© 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. 80376
    Prev
    Next
    INDEX
    Explanations

    EPS file formats

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

    eps and mp files

    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
    ۵
    0.56
     efektif
    0.56
    (
    0.54
     probabilmente
    0.53
     efectivos
    0.52
    فیلم
    0.52
     membro
    0.51
     nigga
    0.51
     ajud
    0.50
     certe
    0.50
    POSITIVE LOGITS
    砶
    0.51
    zip
    0.49
     ці
    0.47
    路
    0.47
    山
    0.47
    that
    0.47
    生成
    0.46
    及
    0.46
    to
    0.46
    subsection
    0.46
    Activations Density 0.000%

    No Known Activations