© 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. 78709
    Prev
    Next
    INDEX
    Explanations

    words with specific following words

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

    retrieval, orchestration, execution, search, partition

    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
    asc
    0.50
    Header
    0.49
     pares
    0.46
     SV
    0.45
    Å
    0.43
    Keeper
    0.43
    chas
    0.43
    res
    0.43
    OfYear
    0.42
     fixes
    0.42
    POSITIVE LOGITS
    桂
    0.54
    ழி
    0.53
    activate
    0.50
    ０
    0.50
    пуль
    0.48
     društ
    0.48
     विफल
    0.48
     कसा
    0.47
    ፐ
    0.47
    гиз
    0.46
    Activations Density 0.000%

    No Known Activations