© 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. 175059
    Prev
    Next
    INDEX
    Explanations

    never let

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

    language origins and scripts

    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
    e
    0.50
    ből
    0.50
     restric
    0.49
    limited
    0.49
    t
    0.49
    restricted
    0.48
    ى
    0.47
    stripe
    0.46
    تيب
    0.46
     limitado
    0.45
    POSITIVE LOGITS
     含
    0.59
     ܗܘ
    0.54
     ע
    0.53
     她
    0.49
     בד
    0.48
     صدی
    0.48
     आस
    0.48
     เหมือน
    0.48
     βα
    0.48
     Հ
    0.48
    Activations Density 0.000%

    No Known Activations