© 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. 48281
    Prev
    Next
    INDEX
    Explanations

    pain points, substitute function, popular voice

    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
    ຫານ
    0.48
     teamTable
    0.48
     আর
    0.47
    萘
    0.46
    ClrBit
    0.45
     cGraph
    0.44
     modalCard
    0.44
    ILTON
    0.44
    unhofer
    0.44
    aksanaan
    0.44
    POSITIVE LOGITS
     to
    0.47
     (
    0.46
     all
    0.45
     Legislation
    0.45
     consecutively
    0.42
     lying
    0.41
     substantially
    0.41
    ट
    0.41
    ↵↵↵
    0.41
    notification
    0.41
    Activations Density 0.000%

    No Known Activations