© 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. 222182
    Prev
    Next
    INDEX
    Explanations

    posting YouTube videos

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

    concepts and specific enumerations

    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
     त्यावेळी
    0.50
    来进行
    0.49
    深夜
    0.48
    ,*/}
    0.48
    時間を
    0.47
     প্রস্তুত
    0.46
     অভিযুক্ত
    0.46
    ]}/
    0.45
    扡
    0.45
     καθη
    0.44
    POSITIVE LOGITS
    s
    0.55
    H
    0.50
    س
    0.49
    Bacteria
    0.47
     Relating
    0.46
    in
    0.45
    er
    0.45
    SPOT
    0.44
    ication
    0.43
    Tottenham
    0.43
    Activations Density 0.000%

    No Known Activations