© 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. 38966
    Prev
    Next
    INDEX
    Explanations

    framework, API, table, concepts

    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
    Conditional
    0.48
     ദേശ
    0.46
     سیاست
    0.44
    siehe
    0.44
     Versand
    0.44
    回应
    0.43
    
    0.43
    پے
    0.43
     Conditional
    0.43
    verbose
    0.42
    POSITIVE LOGITS
    1
    0.54
     lo
    0.47
     fo
    0.47
     and
    0.47
     late
    0.46
     discard
    0.46
     la
    0.46
     desert
    0.45
    PT
    0.45
    5
    0.45
    Activations Density 0.007%

    No Known Activations