© 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. 182712
    Prev
    Next
    INDEX
    Explanations

    shell scripts and commands

    np_acts-logits-general · gemini-2.5-flash-lite

    bash scripts

    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
    apache
    0.49
     canad
    0.47
    explique
    0.46
    andi
    0.44
    android
    0.41
    ාල
    0.40
    .},
    0.40
    canada
    0.40
    csdn
    0.39
    <0x80>
    0.38
    POSITIVE LOGITS
     완료
    0.54
     इन्हे
    0.54
     saucepan
    0.52
     사용
    0.52
     penggunaan
    0.50
     usos
    0.50
     Продол
    0.50
     nozzles
    0.49
     оборудование
    0.49
     استفاده
    0.48
    Activations Density 0.000%

    No Known Activations