© 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. 76974
    Prev
    Next
    INDEX
    Explanations

    Cooperation and comparisons

    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
     melap
    0.47
    u
    0.46
     khiến
    0.45
    i
    0.44
     ril
    0.43
    φάλ
    0.43
     caliber
    0.42
    iak
    0.41
     moulds
    0.41
     upl
    0.40
    POSITIVE LOGITS
     restless
    0.48
     ચૂંટણી
    0.47
    ὕ
    0.46
     실행
    0.45
     कौशल
    0.45
     hopelessly
    0.44
     футболдук
    0.44
    oldsymbol
    0.44
     슈
    0.44
     ፍ
    0.44
    Activations Density 0.002%

    No Known Activations