© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 134526
    Prev
    Next
    INDEX
    Explanations

    str

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     profiling
    0.38
    lub
    0.37
    リズム
    0.37
    ウォー
    0.37
    fit
    0.37
     analysis
    0.36
    ofed
    0.36
     "~
    0.36
    analysis
    0.36
     "[
    0.35
    POSITIVE LOGITS
    此同时
    0.46
     зло
    0.44
    SpriteCollision
    0.43
    avil
    0.39
    Asimismo
    0.39
    okol
    0.39
    untamento
    0.38
     Pologne
    0.38
     ましょう
    0.38
    렸다
    0.37
    Activations Density 0.000%

    No Known Activations