© 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. 77003
    Prev
    Next
    INDEX
    Explanations

    author, author, author

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

    teen features

    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
     volunteering
    0.48
     ionized
    0.46
     histogram
    0.45
     interfacing
    0.44
     면
    0.44
     손
    0.43
     Tuning
    0.43
    ω
    0.43
     TIR
    0.42
     addressing
    0.42
    POSITIVE LOGITS
    ikums
    0.55
    ischem
    0.48
    uí
    0.48
    geführt
    0.47
     ekip
    0.47
    asie
    0.47
     späteren
    0.47
    Seit
    0.46
    Jogo
    0.46
    ikalische
    0.46
    Activations Density 0.000%

    No Known Activations