© 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. 148964
    Prev
    Next
    INDEX
    Explanations

    square meters or days

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

    explaining flaws or issues

    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
     belirli
    0.49
    诚信
    0.48
     geçmiş
    0.47
    aların
    0.45
    怿
    0.45
    geç
    0.45
    өрд
    0.44
     olma
    0.44
     хто
    0.44
    ıml
    0.44
    POSITIVE LOGITS
    ，
    0.53
     repeated
    0.50
    。
    0.47
     perforated
    0.46
    ，$
    0.46
     copying
    0.46
     or
    0.45
     為
    0.45
     copied
    0.45
     treating
    0.44
    Activations Density 0.001%

    No Known Activations