© 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. 165859
    Prev
    Next
    INDEX
    Explanations

    popping up, sits at, method like

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

    cannot provide

    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
    톡
    0.51
     ہل
    0.45
    ՛
    0.43
    keto
    0.43
    inare
    0.42
    те
    0.42
    茯
    0.42
    关注
    0.41
    వర్
    0.41
     మధ్య
    0.40
    POSITIVE LOGITS
     blond
    0.48
     Partly
    0.47
    ätta
    0.45
    の部分
    0.45
     savage
    0.43
     deliberately
    0.43
    Allen
    0.43
    Norman
    0.43
    िटीज
    0.43
    zględ
    0.43
    Activations Density 0.001%

    No Known Activations