© 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. 113440
    Prev
    Next
    INDEX
    Explanations

    percentage description

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

    Creator, scholar types

    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
    کش
    0.47
    ви
    0.46
    یمی
    0.46
    өм
    0.44
    ν
    0.44
    νου
    0.43
    等着
    0.43
    avali
    0.42
     Cheung
    0.42
    ço
    0.42
    POSITIVE LOGITS
     foal
    0.49
    r
    0.47
     คลิก
    0.46
     ต้น
    0.44
     rallying
    0.44
    ামুটি
    0.44
    పై
    0.44
     pirm
    0.44
     idő
    0.43
     Energy
    0.43
    Activations Density 0.000%

    No Known Activations