© 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. 8539
    Prev
    Next
    INDEX
    Explanations

    Audit, Generation, spectrum, melodic, data, voltage, chameleon

    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
    Ժ
    0.39
    ึ
    0.35
    른
    0.35
    观点
    0.35
    irteenth
    0.35
    ษ
    0.35
    อยู่
    0.35
    ๗
    0.34
    Untitled
    0.34
    че
    0.34
    POSITIVE LOGITS
     bonuses
    0.37
     makes
    0.35
     incentives
    0.35
     protects
    0.34
     disinfect
    0.34
     every
    0.34
     all
    0.33
     helps
    0.33
     holes
    0.33
     tellement
    0.33
    Activations Density 0.083%

    No Known Activations