© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71839
    Prev
    Next
    INDEX
    Explanations

    import statements for android

    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_22/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
    她也
    -1.11
    -1.02
     måneder
    -1.02
    CÁ
    -1.01
     ));
    -0.99
    なければ
    -0.96
    -0.96
     esbo
    -0.96
     estri
    -0.94
     alterar
    -0.94
    POSITIVE LOGITS
     nonostante
    0.96
     FUCKING
    0.96
     collaborazione
    0.90
     corr
    0.89
     dunque
    0.88
    ay
    0.85
    unno
    0.85
     avendo
    0.85
     awn
    0.84
    nade
    0.83
    Activations Density 0.009%

    No Known Activations