© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 76277
    Prev
    Next
    INDEX
    Explanations

    parentheses or delimiters

    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
    il
    0.44
    strument
    0.44
    ulin
    0.43
    ದು
    0.43
    ட்ட
    0.42
    jection
    0.42
    š
    0.41
    usus
    0.41
    ż
    0.41
    <0x90>
    0.40
    POSITIVE LOGITS
    㙂
    0.43
     Transparent
    0.41
    Length
    0.41
     Luxury
    0.40
     Couture
    0.39
     Renewable
    0.39
     Lavender
    0.38
    㫴
    0.38
     Therapeutic
    0.38
    嚧
    0.38
    Activations Density 0.006%

    No Known Activations