© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 105940
    Prev
    Next
    INDEX
    Explanations

    physical descriptions of body parts

    np_acts-logits-general · gemini-2.5-flash-lite

    physical descriptors of appearance, particularly adjectives that describe visual attributes like size, color, and texture.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on attributive adjectives and descriptive modifiers (e.g. size, color, shape, texture) that qualify nouns.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     like
    -1.64
     then
    -1.59
     strateg
    -1.48
    gemene
    -1.32
     stup
    -1.27
     krach
    -1.24
     produ
    -1.24
     دیجیتال
    -1.23
     such
    -1.21
    瘣
    -1.14
    POSITIVE LOGITS
    Even
    1.52
    Those
    1.51
    After
    1.41
    Perhaps
    1.41
    Probably
    1.40
    Different
    1.40
     černá
    1.40
    Using
    1.38
    Only
    1.38
    The
    1.35
    Activations Density 0.073%

    No Known Activations