© 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. 42041
    Prev
    Next
    INDEX
    Explanations

    Health, NM, such, whole operation

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

    roles and components

    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
    airplane
    0.47
    𝐪
    0.47
    equations
    0.47
    formulas
    0.46
     уравнения
    0.46
    P
    0.45
    臣
    0.45
     ভাঙ্গা
    0.44
     اختر
    0.43
     |\
    0.43
    POSITIVE LOGITS
    豊かな
    0.50
     rb
    0.48
     landscaped
    0.47
    ,
    0.45
     μεγαλ
    0.43
    サプライ
    0.43
    ј
    0.43
    ને
    0.43
    od
    0.42
    Templ
    0.42
    Activations Density 0.000%

    No Known Activations