© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 50198
    Prev
    Next
    INDEX
    Explanations

    case, number, or punctuation

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

    code and programming contexts

    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
     
    0.48
     Extra
    0.47
     l
    0.47
     Poets
    0.46
     Essay
    0.46
    essay
    0.45
     கூடுதல்
    0.44
     extra
    0.44
     lan
    0.42
     Lebanon
    0.42
    POSITIVE LOGITS
    ُمْ
    0.47
     estoppel
    0.47
    روش
    0.45
    reys
    0.44
     biodivers
    0.44
    詆
    0.44
    فاوت
    0.43
    یدی
    0.42
     fyrir
    0.42
    صل
    0.42
    Activations Density 0.001%

    No Known Activations