© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 227598
    Prev
    Next
    INDEX
    Explanations

    brand names and technology

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    住院
    0.46
     pomeriggio
    0.41
     fungicide
    0.41
    রাও
    0.40
    -(-
    0.40
     agrícolas
    0.40
    躬
    0.39
     $("#"
    0.39
    履行
    0.39
    ＆
    0.38
    POSITIVE LOGITS
    nju
    0.54
     thấp
    0.52
    afu
    0.52
     yn
    0.50
    olls
    0.50
    ında
    0.49
    owego
    0.47
    it
    0.46
    guh
    0.46
    jones
    0.46
    Activations Density 0.000%

    No Known Activations