© 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. 34-GEMMASCOPE-RES-131K
    7. 102445
    Prev
    Next
    INDEX
    Explanations

    free of charge

    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_34/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
     Sush
    -0.86
     Kinetics
    -0.84
     Exter
    -0.84
     recueil
    -0.82
     meil
    -0.81
    فی
    -0.78
    薩
    -0.78
     retorn
    -0.77
    ╞
    -0.77
    okin
    -0.76
    POSITIVE LOGITS
     Noon
    0.82
     szko
    0.81
    ポット
    0.79
    uanto
    0.77
    Übernach
    0.77
    といった
    0.76
    廊下
    0.75
     Tribal
    0.73
    現場
    0.73
    line
    0.73
    Activations Density 0.001%

    No Known Activations