© 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. 197683
    Prev
    Next
    INDEX
    Explanations

    numbers and years

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

    billions of users, revenue, media

    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
    Frequency
    0.56
    Lake
    0.52
    Event
    0.51
    InProgress
    0.51
    읊
    0.51
    Chron
    0.46
    יי
    0.46
    ана
    0.46
    County
    0.46
    全
    0.46
    POSITIVE LOGITS
     ymp
    0.49
    €™
    0.49
     त्यांची
    0.49
    weist
    0.47
     constriction
    0.46
     त्याची
    0.45
     അയാൾ
    0.44
     रुका
    0.44
     그다음에
    0.43
     Loksatta
    0.42
    Activations Density 0.000%

    No Known Activations