© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 136139
    Prev
    Next
    INDEX
    Explanations

    del + noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     el
    0.49
    ión
    0.48
    s
    0.48
    중
    0.48
    the
    0.47
     possibilité
    0.47
    प्र
    0.43
    ástico
    0.43
     do
    0.43
     resultado
    0.43
    POSITIVE LOGITS
     }}=\
    0.47
    antera
    0.46
    |");
    0.46
     рынка
    0.45
    incu
    0.43
    Lc
    0.43
     rynku
    0.43
    ેશન
    0.42
     በኋላ
    0.41
     мм
    0.41
    Activations Density 0.012%

    No Known Activations