© 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. 37297
    Prev
    Next
    INDEX
    Explanations

    availability, times, websites, existence

    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
     culp
    0.45
     commensurate
    0.45
     compacted
    0.44
     gap
    0.42
     compaction
    0.41
     consolidated
    0.41
     penalty
    0.40
     ㅜ
    0.40
     grievances
    0.40
     necrosis
    0.39
    POSITIVE LOGITS
     Certains
    0.49
     Lorsque
    0.49
     Aujourd
    0.49
    idée
    0.49
     Artists
    0.48
     Avec
    0.48
    拍摄
    0.47
     Workshops
    0.47
     Describes
    0.47
     utilisé
    0.47
    Activations Density 0.003%

    No Known Activations