© 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. 53107
    Prev
    Next
    INDEX
    Explanations

    safe on trust

    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
    एको
    0.43
    TypeText
    0.41
    Acad
    0.41
    会自动
    0.40
    نو
    0.40
    或是
    0.39
    academic
    0.39
    =>$
    0.39
    UMO
    0.39
    corper
    0.39
    POSITIVE LOGITS
     treacherous
    0.47
     brutal
    0.46
     zerstört
    0.45
     IST
    0.44
     indestructible
    0.43
     Doug
    0.42
     Donovan
    0.42
     zerst
    0.42
     Brendan
    0.41
     Dogg
    0.41
    Activations Density 0.007%

    No Known Activations