© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 124045
    Prev
    Next
    INDEX
    Explanations

    is followed by descriptive attributes

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

    The neuron detects present-tense third-person singular verbs (like “is,” “offers,” “provides,” “has,” “will”) that introduce product features or descriptions.

    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
     and
    -1.93
    nữ
    -1.41
     japonés
    -1.36
    argentina
    -1.34
    labelControl
    -1.34
     fter
    -1.32
     žena
    -1.32
     primas
    -1.31
     питання
    -1.31
     Temos
    -1.30
    POSITIVE LOGITS
     you
    2.03
     be
    1.68
     my
    1.48
     use
    1.48
    x
    1.45
     suivi
    1.45
     has
    1.45
    A
    1.44
    </th>
    1.43
     was
    1.42
    Activations Density 0.046%

    No Known Activations