© 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-65K
    7. 348
    Prev
    Next
    INDEX
    Explanations

    support muscle

    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_65k_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
    KJ
    0.52
    -
    0.51
    6
    0.51
    kJ
    0.50
    bel
    0.49
    ↵
    0.49
    us
    0.49
    Sig
    0.47
    да
    0.47
    Com
    0.46
    POSITIVE LOGITS
    小題
    0.49
     milking
    0.47
     giường
    0.46
     treetops
    0.44
     Purposes
    0.43
     castes
    0.43
    िमा
    0.43
    綵
    0.42
     Zones
    0.42
    數字
    0.42
    Activations Density 0.001%

    No Known Activations