© 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. 193480
    Prev
    Next
    INDEX
    Explanations

    not allowed

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

    question mark followed by text

    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
    πλ
    0.60
    ὧ
    0.59
    らない
    0.50
    жня
    0.47
     અમારી
    0.46
    私たち
    0.45
    薬
    0.45
     Ва
    0.44
    вався
    0.44
    遛
    0.44
    POSITIVE LOGITS
    에
    0.48
    iak
    0.47
     prosperous
    0.47
    트
    0.45
     ega
    0.44
     RBI
    0.42
    ുമായി
    0.42
     maxSum
    0.42
    ე
    0.42
     ?";
    0.42
    Activations Density 0.001%

    No Known Activations