© 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. 65429
    Prev
    Next
    INDEX
    Explanations

    workshop on forensic sedimentology

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

    subtly hint at attacks or activities

    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
     fomentar
    0.51
    铯
    0.49
    閲覧
    0.47
     ecmaVersion
    0.46
    딘
    0.45
     artik
    0.45
    '$,
    0.45
    豊かな
    0.44
    ज़ा
    0.44
     etcétera
    0.44
    POSITIVE LOGITS
    ional
    0.48
    umal
    0.46
    OM
    0.46
    r
    0.46
    ada
    0.45
    alk
    0.45
    hrs
    0.45
    omi
    0.44
     الرئيسي
    0.44
    ILL
    0.44
    Activations Density 0.000%

    No Known Activations