© 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. 183416
    Prev
    Next
    INDEX
    Explanations

    upper for, money specially, raccoons

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

    Introduce yourself & cash payment

    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
     TRAILS
    0.59
    嬬
    0.57
     modeli
    0.51
    পাকিস্ত
    0.49
    TARGETTING
    0.49
    lcii
    0.49
     DURING
    0.48
    므
    0.48
    ʈ
    0.48
    THE
    0.48
    POSITIVE LOGITS
    ig
    0.46
     heath
    0.45
     Heath
    0.43
    ,
    0.42
    Heath
    0.42
     CJ
    0.41
     Stadium
    0.41
     inconvenience
    0.41
    یز
    0.40
     stadium
    0.40
    Activations Density 0.001%

    No Known Activations