© 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. 42429
    Prev
    Next
    INDEX
    Explanations

    part numbers

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

    structured identifiers

    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
     deceit
    0.45
     indebtedness
    0.44
    обс
    0.42
    럴
    0.41
     ngunit
    0.41
    丛
    0.41
     lakini
    0.40
     tarm
    0.39
     परंतु
    0.39
    ành
    0.39
    POSITIVE LOGITS
     İstanbul
    0.44
     Reykjav
    0.42
     مشہور
    0.41
     whirlpool
    0.39
     ⭐
    0.38
    ຖືກ
    0.38
    ሁሉም
    0.38
    صور
    0.38
    後的
    0.38
     istanbul
    0.38
    Activations Density 0.000%

    No Known Activations