© 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. 141572
    Prev
    Next
    INDEX
    Explanations

    phrase completions

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

    therefore, no changes

    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
    6
    0.50
    ৩৬
    0.49
     varias
    0.48
     Troubles
    0.48
     berbagai
    0.47
    ɪ
    0.46
     Wirklich
    0.46
     Hour
    0.46
     comune
    0.46
    镌
    0.45
    POSITIVE LOGITS
    textit
    0.48
    controls
    0.48
    NO
    0.46
    {}\
    0.45
     প্রত্যা
    0.43
    艶
    0.43
    裄
    0.42
    ად
    0.42
     commuters
    0.41
    formin
    0.41
    Activations Density 0.000%

    No Known Activations