© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 18332
    Prev
    Next
    INDEX
    Explanations

    technical concepts with descriptions

    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_31_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
     पराम
    0.42
    廡
    0.42
    áni
    0.41
     Steering
    0.41
    arser
    0.41
    铠
    0.41
     مصنوعی
    0.41
     тоже
    0.40
    یند
    0.39
     Suggested
    0.39
    POSITIVE LOGITS
     *}
    0.48
     calculates
    0.45
     BECAUSE
    0.45
    ……”
    0.44
    I
    0.43
     exceeds
    0.43
    ResourceId
    0.42
     discrimination
    0.42
    Annual
    0.42
     यदि
    0.42
    Activations Density 0.003%

    No Known Activations