© 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. 9732
    Prev
    Next
    INDEX
    Explanations

    code components or identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    which
    -2.05
     are
    -1.84
     again
    -1.76
     never
    -1.73
     unless
    -1.70
     requiring
    -1.63
     instead
    -1.60
    訁
    -1.59
     didn
    -1.58
     amounting
    -1.57
    POSITIVE LOGITS
    <bos>
    2.23
    Véxase
    1.59
     入り口
    1.56
    antMatchers
    1.53
    ühner
    1.52
    ,  
    1.41
    踽
    1.41
    齣
    1.41
    骤
    1.41
    这一幕
    1.41
    Activations Density 0.000%

    No Known Activations