© 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. 58926
    Prev
    Next
    INDEX
    Explanations

    debut / latest

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

    password policy

    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
    리기
    0.53
    쐞
    0.50
    ଟି
    0.49
    পরিব
    0.47
    ઞ
    0.45
    後に
    0.44
     нужно
    0.44
    保护
    0.44
    人に
    0.43
     виправивши
    0.43
    POSITIVE LOGITS
     डेब्यू
    0.49
     debuted
    0.44
     instalments
    0.43
     debuts
    0.43
     debuting
    0.43
     debut
    0.43
     Platz
    0.42
     বেতন
    0.41
    </th>
    0.41
     مبس
    0.41
    Activations Density 0.000%

    No Known Activations