© 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. 30362
    Prev
    Next
    INDEX
    Explanations

    designed to trick

    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
    也都
    0.46
    那是
    0.44
    rés
    0.44
    separate
    0.44
    <unused464>
    0.44
     தேர்ந்த
    0.43
    re
    0.42
    harma
    0.42
    jelen
    0.42
    aré
    0.42
    POSITIVE LOGITS
     populaire
    0.50
     Friday
    0.50
     Thursday
    0.49
     $\
    0.49
     Math
    0.47
     Teacher
    0.47
     Interactive
    0.47
     MATH
    0.46
     Wednesday
    0.46
     game
    0.46
    Activations Density 0.004%

    No Known Activations