© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 191699
    Prev
    Next
    INDEX
    Explanations

    padre rico / rich father

    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
    🐈
    0.42
    😬
    0.41
    🙌
    0.41
    😄
    0.41
    ($_
    0.40
     😄
    0.39
    //$
    0.39
     graciously
    0.39
    👏👏
    0.38
     டாக்டர்
    0.38
    POSITIVE LOGITS
     pipelines
    0.41
     submersible
    0.39
     softwares
    0.39
    vedo
    0.38
    Li
    0.37
    скоп
    0.37
     le
    0.37
    螢
    0.37
     monitoring
    0.37
     pavements
    0.36
    Activations Density 0.002%

    No Known Activations