© 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. 206232
    Prev
    Next
    INDEX
    Explanations

    reps, cycles, results, experts

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

    websites, primality test, AI

    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
     tokom
    0.48
     occasional
    0.47
    又は
    0.46
     receptions
    0.46
     reciprocal
    0.45
    occas
    0.45
     tijekom
    0.42
     <*>
    0.42
    special
    0.42
    2
    0.41
    POSITIVE LOGITS
    控制器
    0.47
    ركة
    0.46
     कंट्रोल
    0.46
     człowie
    0.45
    Celeron
    0.44
    游戏的
    0.44
     التمث
    0.44
    移动
    0.43
     जंगल
    0.43
    ông
    0.43
    Activations Density 0.001%

    No Known Activations