© 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. 49522
    Prev
    Next
    INDEX
    Explanations

    time may, raw egg, led by

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

    Vapor Pressure

    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
     There
    0.49
     Bingo
    0.48
     bingo
    0.45
     Puj
    0.43
     Tasmania
    0.42
    Bingo
    0.42
    鸾
    0.42
     Sadd
    0.41
     muzik
    0.41
     그다음에
    0.41
    POSITIVE LOGITS
    gür
    0.46
     अहंकार
    0.44
    वें
    0.43
    atique
    0.43
     ductile
    0.43
    abilir
    0.42
    diyl
    0.42
    皚
    0.42
     inductively
    0.42
    boi
    0.42
    Activations Density 0.000%

    No Known Activations