© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7700
    Prev
    Next
    INDEX
    Explanations

    repentance and remorse

    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
    ll
    -2.75
    </strong>
    -2.41
    al
    -2.39
    *
    -2.30
     are
    -2.28
    玙
    -2.25
    N
    -2.25
     said
    -2.14
     *
    -2.11
     ensuing
    -2.11
    POSITIVE LOGITS
    ↵
    2.47
     and
    2.00
     剧照
    1.99
    岽
    1.98
     perna
    1.97
    ╿
    1.91
    蔟
    1.89
     古风
    1.87
    mintaan
    1.86
    ŚĆ
    1.84
    Activations Density 0.003%

    No Known Activations