© 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. 37286
    Prev
    Next
    INDEX
    Explanations

    executable paths

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

    programming language identifiers

    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
    t
    0.58
     때문에
    0.49
    コ
    0.49
    zovaniyu
    0.48
     Mannschaft
    0.47
     Ту
    0.47
    ご注文
    0.47
    YD
    0.47
     Mbappe
    0.46
    บบ
    0.46
    POSITIVE LOGITS
    unehmen
    0.45
    </strong>
    0.43
    ltre
    0.42
     homogen
    0.41
     спри
    0.41
    führen
    0.41
    ž
    0.40
    ến
    0.40
    atea
    0.39
    ionista
    0.39
    Activations Density 0.001%

    No Known Activations