© 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. 145717
    Prev
    Next
    INDEX
    Explanations

    location and specific items

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

    I can/cannot do things

    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
     ṣ
    0.49
    arın
    0.47
    leş
    0.46
    ಯೇ
    0.46
     שלי
    0.46
     ș
    0.46
     исте
    0.46
    distanceArray
    0.46
     другие
    0.45
     ինչ
    0.44
    POSITIVE LOGITS
    ，
    0.50
    从小
    0.46
    CA
    0.46
    Portugal
    0.45
    हाबाद
    0.44
    오
    0.44
    LC
    0.43
     Portugal
    0.43
    auml
    0.43
     Blackjack
    0.42
    Activations Density 0.000%

    No Known Activations