© 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. 19472
    Prev
    Next
    INDEX
    Explanations

    academic publication citations

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

    Unit Price, segments, Messiah

    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
     prostor
    0.44
     ફી
    0.42
    mara
    0.40
    naj
    0.40
     공간
    0.40
    IPAL
    0.40
    舧
    0.40
     যা
    0.39
     nalazi
    0.39
    ANTE
    0.39
    POSITIVE LOGITS
    credited
    0.44
    它们的
    0.41
    名为
    0.41
     vorbere
    0.40
    信用
    0.40
     πί
    0.40
    总体
    0.39
    营业
    0.39
    少
    0.39
     Toxicology
    0.39
    Activations Density 0.000%

    No Known Activations