© 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. 92071
    Prev
    Next
    INDEX
    Explanations

    leading words

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

    critical functions

    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
    ுகிற
    0.52
     collocation
    0.52
     꾸
    0.47
     Small
    0.46
    </
    0.46
    s
    0.46
     quitting
    0.45
     Dun
    0.45
     runt
    0.45
    흔
    0.45
    POSITIVE LOGITS
    gypte
    0.56
    outheast
    0.51
    '$.
    0.49
    νες
    0.49
    𝒗
    0.49
     granddaughters
    0.48
    Philippines
    0.48
    ном
    0.48
    zetac
    0.47
    cientes
    0.47
    Activations Density 0.001%

    No Known Activations