© 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. 40-GEMMASCOPE-2-RES-262K
    7. 191275
    Prev
    Next
    INDEX
    Explanations

    new or under construction

    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_40_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
    传说
    0.45
    Henderson
    0.41
    Writing
    0.38
    枝
    0.38
    ნ
    0.38
     유명
    0.37
     ferm
    0.36
     poesia
    0.36
    Legend
    0.36
    Branches
    0.36
    POSITIVE LOGITS
    úrese
    0.47
     activation
    0.42
    ᒎ
    0.41
    機制
    0.40
     காட்சி
    0.40
    ovaná
    0.39
     trips
    0.39
     TRIP
    0.38
     trip
    0.38
     activations
    0.38
    Activations Density 0.002%

    No Known Activations