© 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. 11415
    Prev
    Next
    INDEX
    Explanations

    reading aloud or reciting specific texts

    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
     квартиру
    -1.36
    UnifiedTopology
    -1.34
     ExecuteAsync
    -1.27
    两个
    -1.26
    AN
    -1.23
     pela
    -1.23
    bių
    -1.22
    ፳
    -1.20
    ないけど
    -1.20
    Each
    -1.18
    POSITIVE LOGITS
    versus
    1.47
    遹
    1.41
     schrij
    1.39
     in
    1.38
    痦
    1.35
     italie
    1.34
    今度は
    1.33
     posible
    1.33
    pejo
    1.31
    俺は
    1.31
    Activations Density 0.021%

    No Known Activations