© 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. 223893
    Prev
    Next
    INDEX
    Explanations

    cannot guarantee security

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

    common questions and responses

    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
    盐
    0.50
    can
    0.49
     discs
    0.48
     hepat
    0.47
    িল্লী
    0.46
     practitioners
    0.45
     medics
    0.45
     enzym
    0.45
     podcasts
    0.45
     physicians
    0.45
    POSITIVE LOGITS
     ausgeführt
    0.52
     ഏറ്റ
    0.51
     hinzuf
    0.50
    اً
    0.50
    乖
    0.50
     affectionate
    0.50
    規則
    0.50
    쾌
    0.49
    っいて
    0.47
     Aunque
    0.46
    Activations Density 0.000%

    No Known Activations