© 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. 75037
    Prev
    Next
    INDEX
    Explanations

    and deceit

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

    actions or consequences

    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
    ሲ
    0.44
     unchanged
    0.44
    (/*
    0.43
    ከ
    0.43
    过后
    0.41
    항
    0.41
    גד
    0.41
    株
    0.41
    дри
    0.41
    бва
    0.41
    POSITIVE LOGITS
    یم
    0.55
     Paintings
    0.53
     Strap
    0.51
     problemi
    0.51
    厚的
    0.51
     ingeniería
    0.50
     Solids
    0.50
     Huskies
    0.50
     Gators
    0.50
     Denim
    0.50
    Activations Density 0.001%

    No Known Activations