© 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. 109077
    Prev
    Next
    INDEX
    Explanations

    keg stacking

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

    explaining code or context

    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
    ih
    0.67
    i
    0.57
    ua
    0.57
    d
    0.55
    ha
    0.54
    z
    0.54
    ode
    0.53
    Um
    0.51
    odie
    0.51
    od
    0.50
    POSITIVE LOGITS
    вок
    0.54
    劍
    0.50
    擴
    0.49
     ভূ
    0.49
    ျေး
    0.48
    氣
    0.47
     ಕಾರ್ಯ
    0.47
    carrito
    0.47
    社會
    0.46
    び
    0.46
    Activations Density 0.000%

    No Known Activations