Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 100372
    Prev
    Next
    INDEX
    Explanations

    private hosted services

    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
    트
    0.52
     replenished
    0.50
     thermocou
    0.50
    t
    0.50
    ніза
    0.47
    electrons
    0.47
    ग्विजय
    0.46
    केमॉन
    0.46
    xcuserdata
    0.46
    cY
    0.46
    POSITIVE LOGITS
     a
    0.67
     
    0.57
     i
    0.56
     S
    0.52
     B
    0.51
     D
    0.51
     K
    0.51
     Recreation
    0.49
     Board
    0.48
     Driver
    0.48
    Activations Density 0.003%

    No Known Activations