© 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. 20354
    Prev
    Next
    INDEX
    Explanations

    most expensive

    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
    ai
    0.53
    organisms
    0.52
    ói
    0.52
    u
    0.51
    pers
    0.48
    boys
    0.47
    remarkable
    0.46
    un
    0.45
    os
    0.44
     organisme
    0.44
    POSITIVE LOGITS
    ９
    0.53
    㪯
    0.48
     October
    0.48
    SSA
    0.47
     ANNUAL
    0.47
     Allocated
    0.47
    PAF
    0.47
     $\$
    0.47
     rightfully
    0.46
     Routed
    0.45
    Activations Density 0.013%

    No Known Activations