© 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. 65138
    Prev
    Next
    INDEX
    Explanations

    Find Your Next Home, His intelligence, Article, Congrats

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

    states and properties

    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
    示
    0.47
     Pen
    0.44
     آم
    0.43
    信号
    0.43
     Biom
    0.42
     COVID
    0.42
     ONU
    0.41
     Valentine
    0.40
     Alternate
    0.40
    ?’
    0.40
    POSITIVE LOGITS
     возраста
    0.58
    aziland
    0.54
    ется
    0.53
    chessboard
    0.52
    surfing
    0.52
    𝟬
    0.52
     describ
    0.52
     individ
    0.51
     третий
    0.51
    sites
    0.51
    Activations Density 0.000%

    No Known Activations