© 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. 62658
    Prev
    Next
    INDEX
    Explanations

    trust company

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

    medical, technical, or descriptive terms

    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
     varying
    0.45
     Vary
    0.44
    орк
    0.44
     referenties
    0.43
    ⵚ
    0.43
     사이
    0.42
     ಮತ್ತು
    0.42
     이하
    0.42
     이름
    0.41
     팔
    0.41
    POSITIVE LOGITS
    Mat
    0.49
     Lorentzian
    0.47
    াতাড়ি
    0.43
     Apk
    0.40
    ','$
    0.40
    ak
    0.40
     Eqs
    0.40
     aplicativos
    0.39
    ai
    0.39
     tinta
    0.39
    Activations Density 0.000%

    No Known Activations