© 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. 28100
    Prev
    Next
    INDEX
    Explanations

    red line

    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
     capillaries
    0.42
     первым
    0.42
     fillets
    0.39
     elsewhere
    0.38
     homomorphisms
    0.38
     abbreviated
    0.37
     dictionaries
    0.37
     "
    0.37
    CharField
    0.37
     মুদ্রা
    0.37
    POSITIVE LOGITS
     ہمیں
    0.57
     jullie
    0.55
     yaar
    0.54
    众人
    0.50
     rampant
    0.49
     ненави
    0.49
     heinous
    0.48
     heartbreaking
    0.48
     nossa
    0.47
     نحن
    0.46
    Activations Density 0.007%

    No Known Activations