© 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. 210345
    Prev
    Next
    INDEX
    Explanations

    core beliefs and positive feelings

    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
    杲
    0.45
    قدم
    0.40
    牘
    0.40
     территории
    0.39
     fotografías
    0.39
    ceding
    0.39
     مشتمل
    0.38
    鳧
    0.38
    摄影
    0.37
    Cotton
    0.37
    POSITIVE LOGITS
     edge
    0.45
     Yoh
    0.43
     Edge
    0.43
    lc
    0.41
     Imp
    0.41
     Launcher
    0.41
     share
    0.40
    ugu
    0.40
     MinMaxScaler
    0.40
     integrated
    0.40
    Activations Density 0.000%

    No Known Activations