© 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-262K
    7. 19907
    Prev
    Next
    INDEX
    Explanations

    make or til

    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_262k_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
     monolith
    0.41
     जिनके
    0.39
    っいて
    0.39
    ａ
    0.38
     Sanskrit
    0.38
    ដូច្ន
    0.37
    梩
    0.37
    iono
    0.36
     विरुद्ध
    0.36
    があ
    0.36
    POSITIVE LOGITS
    Riv
    0.50
    ABET
    0.47
    Charges
    0.47
    https
    0.45
    Insurance
    0.45
    Radians
    0.45
    𝗛
    0.43
     insurance
    0.43
    Cos
    0.43
    BV
    0.42
    Activations Density 0.001%

    No Known Activations