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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 40499
    Prev
    Next
    INDEX
    Explanations

    API, free, McAffee, dream, worlds

    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
     veya
    0.55
    したり
    0.51
     &/
    0.49
     или
    0.47
     किंवा
    0.46
     अथवा
    0.45
    :\
    0.45
    或者
    0.45
    または
    0.45
     અથવા
    0.44
    POSITIVE LOGITS
     বাকি
    0.43
     بہترین
    0.43
     révolution
    0.43
     bellissimo
    0.43
     Vielzahl
    0.42
     semblent
    0.41
     surpre
    0.41
     extravaganza
    0.41
     লাভ
    0.41
     Jahres
    0.41
    Activations Density 0.003%

    No Known Activations