© 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. 36715
    Prev
    Next
    INDEX
    Explanations

    identifies actions or descriptions

    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
    ש
    0.61
    শন
    0.51
    ರಲ್ಲಿ
    0.51
    ק
    0.51
     semplice
    0.49
     croit
    0.48
    Clark
    0.48
    आधी
    0.47
     praia
    0.47
    ו
    0.46
    POSITIVE LOGITS
     heterogeneity
    0.47
     heterogeneous
    0.45
     macarons
    0.42
     Karma
    0.41
     contamination
    0.40
     Caramel
    0.40
     caroten
    0.39
     oligos
    0.39
     wavefunction
    0.39
     carcinogenesis
    0.39
    Activations Density 0.000%

    No Known Activations