© 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. 193732
    Prev
    Next
    INDEX
    Explanations

    specific locations or entities

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

    requires transport or feedback

    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
     лидер
    0.45
     Cordova
    0.45
     Concepción
    0.45
     vitória
    0.42
    痪
    0.42
     ذریع
    0.42
     rightful
    0.42
     وګټ
    0.42
     लाइ
    0.41
     videojuegos
    0.41
    POSITIVE LOGITS
    Clin
    0.56
    Wide
    0.49
    These
    0.48
    簡
    0.48
    str
    0.47
    Democratic
    0.46
    Str
    0.46
    instr
    0.45
    Ordinary
    0.45
    Applic
    0.44
    Activations Density 0.000%

    No Known Activations