© 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. 161557
    Prev
    Next
    INDEX
    Explanations

    numbers and citations

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

    code formatting and 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
    𝗛
    0.48
    𝟯
    0.48
    𝗹
    0.47
    ሎችን
    0.46
    merzen
    0.46
    𝗷
    0.45
    悧
    0.45
    𝗵
    0.44
    𝗶
    0.44
    ewords
    0.43
    POSITIVE LOGITS
     Meridian
    0.49
    国の
    0.48
    рка
    0.47
    次は
    0.47
    ห
    0.47
     selecciona
    0.46
     страны
    0.46
     păr
    0.46
     тел
    0.46
    ิ
    0.46
    Activations Density 0.000%

    No Known Activations