© 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. 195565
    Prev
    Next
    INDEX
    Explanations

    trap and lock

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

    funny, easy peasy, museum

    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
     degeneration
    0.47
    താ
    0.45
    koľ
    0.43
    vered
    0.43
    ěru
    0.43
     Channel
    0.42
    琍
    0.41
     Federated
    0.41
    ர்வ
    0.41
     Ver
    0.40
    POSITIVE LOGITS
    ג
    0.54
    Usu
    0.52
    دیا
    0.52
     Москов
    0.50
    TRANSFER
    0.47
    িসহ
    0.46
    KEYS
    0.46
    INDUST
    0.46
     SUCH
    0.46
    PEND
    0.45
    Activations Density 0.000%

    No Known Activations