© 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-65K
    7. 10480
    Prev
    Next
    INDEX
    Explanations

    use, draw, channel, techniques, ready

    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_65k_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
    JScripts
    0.49
    亣
    0.49
    आउट
    0.49
    ErrorClazz
    0.48
    ᚨ
    0.48
    <unused1012>
    0.47
     pushedAt
    0.47
    üedad
    0.46
    EnglishMarks
    0.46
    湪
    0.46
    POSITIVE LOGITS
     will
    0.50
    ’
    0.49
     respective
    0.46
     .
    0.43
     là
    0.43
     thereafter
    0.43
     proprietor
    0.43
     the
    0.43
     &
    0.42
     Propri
    0.42
    Activations Density 0.009%

    No Known Activations