© 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. 135278
    Prev
    Next
    INDEX
    Explanations

    ordering installation programs

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

    source and destination sheets

    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
    ź
    0.49
    èn
    0.47
    zeichen
    0.45
     buch
    0.45
    ها
    0.45
    ك
    0.45
    ês
    0.44
    buch
    0.43
    straße
    0.43
    š
    0.43
    POSITIVE LOGITS
    %);
    0.50
    )))
    0.47
     ratios
    0.47
    %)
    0.46
     hsize
    0.43
     proportions
    0.43
    %).
    0.42
     শতকরা
    0.42
     சதவீ
    0.41
     parameters
    0.41
    Activations Density 0.000%

    No Known Activations