© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 36428
    Prev
    Next
    INDEX
    Explanations

    introduction prefixes

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

    conditional logic and code structure

    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
    Charged
    0.41
    リー
    0.40
    본
    0.39
    TR
    0.38
    ത്ത്
    0.38
    නා
    0.38
     expiry
    0.38
    Lin
    0.37
     unrealistic
    0.37
     الاسم
    0.37
    POSITIVE LOGITS
    ୍କ
    0.57
     brunes
    0.56
    ments
    0.53
     मोहो
    0.52
    狧
    0.51
    roots
    0.51
    抂
    0.50
     Kow
    0.50
    ępow
    0.49
     cowboys
    0.48
    Activations Density 0.000%

    No Known Activations