© 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. 78975
    Prev
    Next
    INDEX
    Explanations

    direct links and downloads

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

    direct and related concepts

    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
    рт
    0.47
    s
    0.47
    sdag
    0.46
    ாக
    0.45
     processor
    0.45
    чы
    0.43
    itom
    0.43
    ть
    0.43
     readme
    0.43
     ਸੀ
    0.42
    POSITIVE LOGITS
    Direct
    0.67
     Direct
    0.63
     прямой
    0.54
     unteren
    0.54
    DIRECT
    0.52
     डायरेक्ट
    0.51
     直
    0.51
    ---’
    0.49
     пря
    0.48
    Popular
    0.47
    Activations Density 0.011%

    No Known Activations