© 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. 31-GEMMASCOPE-2-RES-65K
    7. 3836
    Prev
    Next
    INDEX
    Explanations

    personalize, parameters, longer latency

    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_31_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
    UARY
    0.52
     эксплуатации
    0.48
    дила
    0.47
    ături
    0.46
    ácie
    0.45
    стями
    0.45
    
    0.45
    ád
    0.45
    史
    0.44
    ueur
    0.44
    POSITIVE LOGITS
     Joe
    0.57
     hat
    0.53
     soup
    0.50
     Cookies
    0.50
     ve
    0.48
     Soy
    0.46
     v
    0.46
     Kame
    0.46
     gå
    0.46
     Chess
    0.46
    Activations Density 0.000%

    No Known Activations