© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 41-GEMMASCOPE-2-RES-262K
    4. 32678
    Prev
    Next
    INDEX
    Explanations

    data, context, history, trends

    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_all/layer_41_width_262k_l0_big
    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
     socalled
    0.40
     variabile
    0.38
    ﺴ
    0.38
    ുവരി
    0.36
    ौनक
    0.36
     constituyen
    0.35
     variáveis
    0.35
     आफ्
    0.35
     vermiş
    0.34
     spacerItem
    0.34
    POSITIVE LOGITS
    -
    0.61
    -.
    0.57
    -)
    0.53
    -%
    0.48
    -,
    0.47
    ueroa
    0.47
    -$
    0.46
     …
    0.44
    -${
    0.43
    -;
    0.43
    Activations Density 0.006%

    No Known Activations