© 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. 70651
    Prev
    Next
    INDEX
    Explanations

    fireflies, ladybugs, flying squirrels

    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
    рована
    0.43
    ノ
    0.42
     surveillance
    0.41
    合
    0.41
    ATE
    0.40
    、
    0.40
     border
    0.40
     vertex
    0.39
     tratt
    0.39
    當時
    0.39
    POSITIVE LOGITS
     ليه
    0.47
     اطلاع
    0.45
     interesa
    0.45
     interessa
    0.44
     방법에
    0.44
    恚
    0.44
     pourquoi
    0.44
    effectiveness
    0.43
    ŭ
    0.43
     эффектив
    0.42
    Activations Density 0.007%

    No Known Activations