© 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. 141846
    Prev
    Next
    INDEX
    Explanations

    business, XYZ, revised, friendly, more, ladies

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

    mathematical fractions or delimiters

    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
    ګ
    0.51
    ائل
    0.49
    تقل
    0.48
    ים
    0.48
    ães
    0.48
    ግ
    0.47
    נ
    0.47
    աբ
    0.47
    何を
    0.47
    END
    0.46
    POSITIVE LOGITS
    amata
    0.45
     Drury
    0.44
     apt
    0.44
     coop
    0.44
     pen
    0.43
     chipset
    0.43
     "*****
    0.43
    ሯ
    0.42
     đèn
    0.42
     octagon
    0.42
    Activations Density 0.001%

    No Known Activations