© 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. 56282
    Prev
    Next
    INDEX
    Explanations

    domain registration details

    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
    古屋
    0.51
    Painted
    0.49
    坎
    0.46
    Residual
    0.46
     দেখিল
    0.46
    Leaves
    0.46
    Establishing
    0.46
    ruf
    0.45
    发展的
    0.45
    Eval
    0.45
    POSITIVE LOGITS
     noisy
    0.46
     captions
    0.44
     attracts
    0.42
     macar
    0.41
     beep
    0.40
     bors
    0.39
    t
    0.39
     entity
    0.39
     skinny
    0.38
     tickers
    0.38
    Activations Density 0.014%

    No Known Activations