© 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. 202761
    Prev
    Next
    INDEX
    Explanations

    subquery

    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
    1
    0.49
    றி
    0.47
    吕
    0.46
    8
    0.46
     મૂળ
    0.44
    期间
    0.42
    Broad
    0.42
    ir
    0.42
     Broad
    0.41
     Medieval
    0.41
    POSITIVE LOGITS
    ²',
    0.50
    bufs
    0.50
     inflict
    0.47
    Venue
    0.45
    operators
    0.44
     ravine
    0.44
    ئیں۔
    0.44
     deplete
    0.44
     drugi
    0.43
    ಣಿ
    0.43
    Activations Density 0.003%

    No Known Activations