© 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. 219544
    Prev
    Next
    INDEX
    Explanations

    grouping or listing items

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

    ends with parenthesis

    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
    ！（
    0.49
    》（
    0.44
    ...(
    0.42
    ))(
    0.40
     $($
    0.40
     (
    0.38
    )}(
    0.38
    」（
    0.38
    FuncName
    0.37
    )}(\
    0.37
    POSITIVE LOGITS
    uah
    0.39
    cón
    0.38
     yaitu
    0.38
    occ
    0.38
    enci
    0.37
    ofsky
    0.37
    FUENTE
    0.36
    anzi
    0.36
    arca
    0.36
    6
    0.36
    Activations Density 0.041%

    No Known Activations