© 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. 68279
    Prev
    Next
    INDEX
    Explanations

    numbers followed by statements

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

    making policy decisions

    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
    eu
    0.51
    mé
    0.49
    Mere
    0.49
    tiger
    0.46
    mer
    0.46
    mw
    0.45
    tss
    0.45
    尘
    0.44
    mere
    0.44
    czech
    0.43
    POSITIVE LOGITS
     omissions
    0.47
    ग्र
    0.45
     Silverado
    0.45
     Fridays
    0.45
     VAS
    0.45
     श्रद्धालुओं
    0.43
     criado
    0.43
     Dri
    0.43
     एफ
    0.42
     तहसीलदार
    0.42
    Activations Density 0.001%

    No Known Activations