© 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. 19669
    Prev
    Next
    INDEX
    Explanations

    dates, specific identifiers, or important follow-ups

    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
    5
    0.47
    7
    0.46
    н
    0.46
    ный
    0.45
    ৫
    0.44
    six
    0.44
    нга
    0.43
    five
    0.42
    8
    0.40
    ха
    0.40
    POSITIVE LOGITS
     kombin
    0.47
     sintomi
    0.47
     hàm
    0.43
     vállalat
    0.42
    相続
    0.41
     combinations
    0.41
     quantidades
    0.41
    分散
    0.39
     quantités
    0.39
    }^{*}
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.