© 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. 121617
    Prev
    Next
    INDEX
    Explanations

    user or return

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

    explaining word usage or definitions

    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
    тических
    0.56
     elektry
    0.51
     léka
    0.51
    ד
    0.49
    <unused680>
    0.49
    ClFN
    0.48
    டர்
    0.48
    तिहासिक
    0.48
    ራዊ
    0.48
    <unused523>
    0.47
    POSITIVE LOGITS
    options
    0.48
    /
    0.44
    optional
    0.44
    Options
    0.44
     User
    0.42
     Optional
    0.41
     /
    0.41
     Mandatory
    0.40
     A
    0.40
     Eco
    0.40
    Activations Density 0.001%

    No Known Activations