© 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. 87651
    Prev
    Next
    INDEX
    Explanations

    chosen field

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

    record or definition list

    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
    તિહાસ
    0.47
     soov
    0.46
    eOut
    0.44
    дви
    0.43
     Herald
    0.43
    یدر
    0.43
    듑
    0.43
     Mih
    0.43
     démontré
    0.43
     subunit
    0.42
    POSITIVE LOGITS
     quando
    0.51
    forder
    0.50
     我的
    0.48
    nya
    0.47
     עד
    0.46
     коли
    0.46
    (*)
    0.46
    sframe
    0.46
    Metric
    0.45
    NESS
    0.45
    Activations Density 0.000%

    No Known Activations