© 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. 139268
    Prev
    Next
    INDEX
    Explanations

    and after remaining

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

    communication, weak or absent, inter-between, notes-ology, supporting hundreds, friends

    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
     Tamaño
    0.55
     Patience
    0.51
    </h3>
    0.47
    🠀
    0.46
     مُ
    0.46
     ഭൂ
    0.45
     létre
    0.44
     الذه
    0.43
     બા
    0.42
    來到
    0.42
    POSITIVE LOGITS
    chemic
    0.53
    밉
    0.47
    devkit
    0.45
     conversations
    0.44
    ision
    0.43
     dopiero
    0.43
    hydroxyl
    0.43
    albeit
    0.43
    ovač
    0.43
    Демо
    0.42
    Activations Density 0.000%

    No Known Activations