© 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. 40756
    Prev
    Next
    INDEX
    Explanations

    To provide, give, let, open

    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
    ışt
    0.48
    茥
    0.48
    ată
    0.46
    inom
    0.46
    Feng
    0.46
    ıt
    0.45
    öhn
    0.45
     உலோக
    0.44
    ид
    0.44
    ặp
    0.44
    POSITIVE LOGITS
     @
    0.45
     msg
    0.44
     contacts
    0.44
     enables
    0.43
     enable
    0.43
     subsidy
    0.42
     I
    0.42
     venu
    0.42
     amu
    0.42
     jobs
    0.42
    Activations Density 0.002%

    No Known Activations