© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 78166
    Prev
    Next
    INDEX
    Explanations

    hosting Denmark

    np_acts-logits-general · gemini-2.5-flash-lite

    historical context, args, its habitat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    owała
    0.55
    বের
    0.49
    ędzynarod
    0.47
    
    0.46
     활동
    0.45
    امت
    0.44
    nelles
    0.44
    müşt
    0.44
    ômes
    0.44
     czł
    0.44
    POSITIVE LOGITS
     risking
    0.49
     compounded
    0.44
     punishing
    0.41
     alqu
    0.41
     adelant
    0.40
     compounding
    0.40
     cuya
    0.40
     >
    0.40
    eco
    0.40
     expend
    0.39
    Activations Density 0.001%

    No Known Activations