© 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. 90125
    Prev
    Next
    INDEX
    Explanations

    (BUSINESS WIRE)

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

    coupon book ideas

    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
    ДО
    0.46
    ದೇ
    0.45
    Р
    0.45
    或其他
    0.45
    قدم
    0.44
    lib
    0.43
    vault
    0.43
    ૂત
    0.43
    لمانية
    0.43
    archiwizowane
    0.43
    POSITIVE LOGITS
    -
    0.47
     tái
    0.46
     πληροφο
    0.46
     החד
    0.46
     nuovo
    0.44
    ıyordu
    0.44
    坳
    0.43
     nieuwe
    0.43
     увеличения
    0.42
     informacija
    0.41
    Activations Density 0.000%

    No Known Activations