© 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. 47217
    Prev
    Next
    INDEX
    Explanations

    administrators keep track of changes

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

    distance between subsequences

    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
    жом
    0.49
     стан
    0.46
     успех
    0.45
     construye
    0.45
    芜
    0.44
     دقی
    0.44
     страницу
    0.44
     mendapatkan
    0.43
     гене
    0.43
     देशी
    0.43
    POSITIVE LOGITS
     de
    0.46
     a
    0.44
     o
    0.43
    bold
    0.42
    ريف
    0.41
     reluct
    0.41
     sparsely
    0.41
     roya
    0.41
    مرة
    0.41
     uninhab
    0.41
    Activations Density 0.000%

    No Known Activations