© 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. 154693
    Prev
    Next
    INDEX
    Explanations

    betting news

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

    `IPsec`, `Matrix`, `Video`, `Label`, `local`

    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
    };
    0.45
     می‌توانید
    0.45
    ſe
    0.44
    至
    0.44
    从此
    0.44
    ,
    0.43
     توانید
    0.43
    异
    0.43
    שו
    0.42
     mellow
    0.42
    POSITIVE LOGITS
    ceiver
    0.49
    Lim
    0.46
     करणे
    0.45
    ๔
    0.44
    fails
    0.43
    Cycles
    0.43
     சரிய
    0.43
    พลัง
    0.43
    剞
    0.43
     осуществляется
    0.42
    Activations Density 0.001%

    No Known Activations