© 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. 188115
    Prev
    Next
    INDEX
    Explanations

    other kind of posts

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

    protein encoded, more objective, is located

    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
    䟧
    0.50
     Первая
    0.50
    Primera
    0.45
    Term
    0.45
     필요
    0.44
     نیاز
    0.43
     گاه
    0.43
    颛
    0.43
    ₁
    0.43
    वर्तमान
    0.42
    POSITIVE LOGITS
     amigas
    0.47
    ává
    0.46
    ujú
    0.45
     hú
    0.45
    ίζουν
    0.44
    vér
    0.44
     poorer
    0.43
    ături
    0.43
    oying
    0.43
    licky
    0.43
    Activations Density 0.003%

    No Known Activations