© 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. 91544
    Prev
    Next
    INDEX
    Explanations

    field ofsurfing orsurface gofirst draftsingular formdistrict, which

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

    data and technical operation concepts

    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
     órg
    0.54
     Towns
    0.54
    嫉
    0.54
    复
    0.51
    miş
    0.51
    ফোঁ
    0.49
     Aś
    0.47
     ′
    0.47
     AWARD
    0.47
     XHTML
    0.47
    POSITIVE LOGITS
    Estoy
    0.53
    Siempre
    0.52
    Estamos
    0.48
    Variety
    0.48
    clide
    0.48
     ಪ್ರಯತ್ನ
    0.48
    ettiin
    0.47
    ่
    0.47
    spanning
    0.47
    Wey
    0.47
    Activations Density 0.001%

    No Known Activations