© 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. 191502
    Prev
    Next
    INDEX
    Explanations

    action verbs and processes

    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
     करार
    0.42
     둘
    0.41
     запу
    0.39
    ورا
    0.38
    ሮች
    0.38
     waren
    0.36
    ьера
    0.36
    Outputs
    0.36
    들을
    0.35
    늑
    0.35
    POSITIVE LOGITS
    shank
    0.40
    sky
    0.40
    ကိုယ်
    0.39
     surely
    0.39
     Linda
    0.39
     Doris
    0.38
     HDMI
    0.38
    sql
    0.38
     Peggy
    0.38
     Shank
    0.37
    Activations Density 0.000%

    No Known Activations