© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 54335
    Prev
    Next
    INDEX
    Explanations

    hitmen, Dungeon Master

    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
     aplicada
    0.52
    َہ
    0.49
     aplicado
    0.48
    et
    0.47
    limit
    0.45
    instrument
    0.45
    replace
    0.43
    OMET
    0.43
     різних
    0.43
    :[
    0.42
    POSITIVE LOGITS
     blazer
    0.45
     banter
    0.43
     mantienen
    0.43
     alerts
    0.42
     constate
    0.42
     leucine
    0.42
     wary
    0.41
     wholesalers
    0.41
     reacted
    0.41
     hardcore
    0.41
    Activations Density 0.031%

    No Known Activations