© 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-65K
    4. 731
    Prev
    Next
    INDEX
    Explanations

    n < 0

    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_65k_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
     Whit
    0.39
     dens
    0.39
     Levi
    0.39
     justamente
    0.39
    
    0.38
     atento
    0.38
     steamers
    0.38
     creek
    0.38
     Bangor
    0.38
     القاعد
    0.38
    POSITIVE LOGITS
    בר
    0.48
    Giovanni
    0.41
    га
    0.38
    acağız
    0.38
    racht
    0.38
    짊
    0.36
    बी
    0.36
    春节
    0.36
    Madrid
    0.36
     olacaktır
    0.36
    Activations Density 0.014%

    No Known Activations