© 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. 124142
    Prev
    Next
    INDEX
    Explanations

    after punctuation

    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
    :
    -1.80
    ;
    -1.73
    )
    -1.52
     –
    -1.46
     really
    -1.45
     different
    -1.43
     essentially
    -1.42
     presumably
    -1.38
     an
    -1.35
     a
    -1.34
    POSITIVE LOGITS
    RAINE
    1.45
    kompet
    1.44
    .../
    1.42
    .°
    1.41
     Mereka
    1.27
     ￥
    1.27
     mereka
    1.26
     Asie
    1.26
     raiſ
    1.25
    voyez
    1.25
    Activations Density 0.048%

    No Known Activations