© 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. 108162
    Prev
    Next
    INDEX
    Explanations

    contrast and comparison

    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
    Sorted
    0.43
    unbox
    0.43
    boxed
    0.40
     sorted
    0.39
     Vessel
    0.39
     granulation
    0.39
    )_{
    0.38
    operand
    0.38
    刓
    0.38
    Cxt
    0.37
    POSITIVE LOGITS
     carnage
    0.47
     Grâce
    0.47
     willfully
    0.44
     outrageous
    0.43
     modernist
    0.43
     nationalist
    0.42
     proclamation
    0.42
     inciting
    0.42
     Riot
    0.42
     police
    0.42
    Activations Density 0.011%

    No Known Activations