© 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. 202606
    Prev
    Next
    INDEX
    Explanations

    liquid metal lacquer

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

    Server code and products

    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
    padx
    0.52
    hsl
    0.46
    :<
    0.45
    ০০
    0.45
    dropDown
    0.45
    fromCharCode
    0.45
    ęt
    0.44
     pathologies
    0.44
     са
    0.43
     prés
    0.43
    POSITIVE LOGITS
    רא
    0.52
     आश
    0.52
    s
    0.49
    و
    0.49
    UND
    0.49
    ുടെ
    0.48
    ود
    0.48
     HONOR
    0.48
    પ
    0.46
     Gewinn
    0.45
    Activations Density 0.000%

    No Known Activations