© 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. 161968
    Prev
    Next
    INDEX
    Explanations

    extended warranty

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

    GPT explanations

    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
     tennis
    0.51
    se
    0.50
     veterinary
    0.49
     seashore
    0.49
     advisory
    0.49
    <u>
    0.47
    SpawnEntry
    0.44
     ophthalm
    0.43
    <strong>
    0.42
    {{
    0.42
    POSITIVE LOGITS
    อรี่
    0.50
    芊
    0.46
    攽
    0.46
    графія
    0.45
    泯
    0.44
     strutt
    0.44
    ಲಾಗಿದೆ
    0.44
     पॉलिटी
    0.44
    ресенье
    0.43
    奸
    0.43
    Activations Density 0.001%

    No Known Activations