© 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. 189192
    Prev
    Next
    INDEX
    Explanations

    my child/ward

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

    data, material, Goliath, evaluation, health, risk

    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
    ᕋ
    0.49
     presumptive
    0.47
     cornerstone
    0.47
     kampung
    0.46
     mutable
    0.46
    閇
    0.46
     সংসার
    0.46
     conversational
    0.45
    鋰
    0.44
    تهای
    0.44
    POSITIVE LOGITS
    Institut
    0.52
     повер
    0.49
     finanzi
    0.49
    ills
    0.48
    SError
    0.48
    ACK
    0.47
     Gé
    0.45
    Universität
    0.45
    ROY
    0.45
    OfDeath
    0.44
    Activations Density 0.001%

    No Known Activations