© 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. 62484
    Prev
    Next
    INDEX
    Explanations

    Liberal values, discuss, section

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

    giving birth to live young

    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
    煐
    0.49
    Burn
    0.48
     svým
    0.48
    疃
    0.44
    FieldError
    0.44
     PSY
    0.44
     Girl
    0.44
    數位
    0.44
    Werk
    0.43
    負
    0.43
    POSITIVE LOGITS
    tm
    0.52
    stractions
    0.50
     happenings
    0.50
    nil
    0.49
     hectares
    0.49
    mm
    0.49
     amendments
    0.48
     ಹಾ
    0.47
    shen
    0.47
    aya
    0.47
    Activations Density 0.000%

    No Known Activations