© 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. 218606
    Prev
    Next
    INDEX
    Explanations

    connecting segments

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

    routine information processing

    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
    گری
    0.48
    事实上
    0.46
     آئے
    0.46
     deliberations
    0.45
    ګ
    0.45
     آپریشن
    0.43
     तयारी
    0.43
    筹
    0.43
    یدی
    0.43
    已经是
    0.43
    POSITIVE LOGITS
     synchron
    0.57
     darstellen
    0.57
    houden
    0.51
     nennen
    0.51
     schlecht
    0.50
     券
    0.49
     synchrotron
    0.49
    stellen
    0.48
     Malibu
    0.48
    seit
    0.48
    Activations Density 0.001%

    No Known Activations