© 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. 245017
    Prev
    Next
    INDEX
    Explanations

    quality and diverse categories

    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
     اندر
    0.45
     '[
    0.44
     tồn
    0.44
    eren
    0.44
     সো
    0.44
     برو
    0.43
     дам
    0.43
     ရ
    0.42
     reluctance
    0.42
     обязан
    0.42
    POSITIVE LOGITS
     Ghulam
    0.45
    ק
    0.45
    בי
    0.44
    democratic
    0.44
    passed
    0.44
    קת
    0.43
    ಝ
    0.43
    Z
    0.43
    კ
    0.42
    initiated
    0.42
    Activations Density 0.000%

    No Known Activations