© 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. 128285
    Prev
    Next
    INDEX
    Explanations

    securely, thick, next, window, baby

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

    capturing personalized canvas amount of real

    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
     :
    0.50
    -%
    0.49
    ochastic
    0.48
    -',
    0.45
     жур
    0.44
    hood
    0.44
    quest
    0.44
     Pooling
    0.44
     kcal
    0.44
     मींस
    0.43
    POSITIVE LOGITS
    বিত্র
    0.57
    一天
    0.53
    ला
    0.52
    بان
    0.51
    м
    0.51
    šao
    0.50
    什么
    0.50
    締め
    0.50
    бил
    0.49
    дения
    0.48
    Activations Density 0.000%

    No Known Activations