© 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. 48618
    Prev
    Next
    INDEX
    Explanations

    exploring relationships and ideas

    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
    setBadgeText
    0.57
     joke
    0.52
    Joke
    0.50
    Resposta
    0.49
    ज़ार
    0.48
     ማለት
    0.47
    ที่
    0.46
     ב
    0.46
     BadRequest
    0.46
     humour
    0.45
    POSITIVE LOGITS
    一把
    0.46
    هي
    0.46
     pensamientos
    0.44
     nain
    0.41
    م
    0.41
    ឧប
    0.40
    hui
    0.40
     olvid
    0.40
     dolores
    0.40
    审查
    0.40
    Activations Density 0.003%

    No Known Activations