© 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. 120282
    Prev
    Next
    INDEX
    Explanations

    lists within brackets

    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
    毫无
    0.35
    ं
    0.35
     алфа
    0.34
     بالغ
    0.34
     बावजूद
    0.34
    谈
    0.33
    imura
    0.33
     uș
    0.33
     nigdy
    0.33
    喩
    0.33
    POSITIVE LOGITS
    <i>
    0.39
    を
    0.38
    に関しては
    0.38
    সক
    0.36
     [
    0.35
     &(
    0.35
     ជា
    0.35
    出現
    0.34
     [(
    0.34
    tempat
    0.34
    Activations Density 0.138%

    No Known Activations