© 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. 164078
    Prev
    Next
    INDEX
    Explanations

    album album

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

    character data, guide, calculates

    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
     instit
    0.49
    servlet
    0.49
    ቛ
    0.49
    ের
    0.48
     শিক্ষক
    0.48
    舘
    0.48
    收入
    0.47
     revêt
    0.47
     inzwischen
    0.47
    تقديم
    0.47
    POSITIVE LOGITS
     cyclones
    0.47
     turb
    0.45
     that
    0.44
     streamlines
    0.44
     champagne
    0.43
     Matcha
    0.42
    ?
    0.41
     truffle
    0.41
     constructs
    0.41
     macarons
    0.40
    Activations Density 0.000%

    No Known Activations