© 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. 22-GEMMASCOPE-RES-131K
    4. 10814
    Prev
    Next
    INDEX
    Explanations

    description + material

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

    The neuron responds to descriptive modifiers—especially adjectives indicating material properties or other salient qualities of a noun.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     Trouvez
    -1.45
    ________,
    -1.43
     Asegúrese
    -1.39
     pite
    -1.38
    ヌード
    -1.34
    ícias
    -1.34
     BANKS
    -1.33
    눙
    -1.32
     urch
    -1.32
    殽
    -1.31
    POSITIVE LOGITS
     and
    2.45
     from
    1.63
     with
    1.40
     all
    1.35
     of
    1.32
     Gnade
    1.16
     ALL
    1.16
     both
    1.13
     Two
    1.13
     or
    1.09
    Activations Density 0.273%

    No Known Activations