© 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. 74271
    Prev
    Next
    INDEX
    Explanations

    animal mauling

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

    explaining with 'instead'

    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
     m
    0.55
     م
    0.54
    <0x0D>
    0.54
     מ
    0.52
    ••
    0.51
    -
    0.50
    0.49
     м
    0.48
     everywhere
    0.48
    -+
    0.46
    POSITIVE LOGITS
    hetam
    0.52
    otives
    0.48
     ખાસ
    0.47
     pabbaj
    0.47
    жета
    0.47
     Verbind
    0.47
    ләре
    0.47
    hehi
    0.47
    譁
    0.47
    ată
    0.46
    Activations Density 0.001%

    No Known Activations