© 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. 101730
    Prev
    Next
    INDEX
    Explanations

    code syntax and operations

    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
    рифмети
    0.57
    Preis
    0.53
    граф
    0.50
     Sereth
    0.50
    ändern
    0.47
    Noeud
    0.47
    faulse
    0.46
    䄳
    0.46
     рекоменду
    0.46
    钏
    0.46
    POSITIVE LOGITS
     shadows
    0.48
     news
    0.47
    -
    0.47
     children
    0.46
     le
    0.46
     lo
    0.43
     light
    0.43
     grandchildren
    0.42
     lettuce
    0.41
     revived
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.