© 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. 112308
    Prev
    Next
    INDEX
    Explanations

    plan questions

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

    units of measurement

    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
    可持续
    0.45
    链
    0.45
     sozialen
    0.43
    此事
    0.43
    \"]\
    0.43
    ುತ್ತಿದ್ದ
    0.43
     социальных
    0.42
    кість
    0.41
     социальной
    0.41
    รก
    0.40
    POSITIVE LOGITS
    i
    0.53
    dummies
    0.48
    patent
    0.47
    NSInteger
    0.45
    royal
    0.45
    printf
    0.44
    ovaní
    0.44
    lors
    0.44
    u
    0.44
    m
    0.44
    Activations Density 0.001%

    No Known Activations