© 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. 158218
    Prev
    Next
    INDEX
    Explanations

    stacker, leading positioning, certainly got

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

    InsightForge

    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
    elolaan
    0.46
    новить
    0.45
     "
    0.43
    дро
    0.42
    と思う
    0.41
     GSE
    0.40
     forgiveness
    0.40
    inuation
    0.40
     Galile
    0.39
    नॉ
    0.39
    POSITIVE LOGITS
    য়ং
    0.51
    格
    0.48
     hà
    0.48
     nacimiento
    0.47
    ベージュ
    0.47
     ביק
    0.46
     dugg
    0.46
    筫
    0.45
     surgi
    0.45
    뺑
    0.45
    Activations Density 0.001%

    No Known Activations