© 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. 165742
    Prev
    Next
    INDEX
    Explanations

    comparison, relative, potential, brainstorm

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

    provides a, less about, going to, con bigger, Black person

    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
    ہ
    0.44
    ７
    0.44
    
    0.44
    ln
    0.43
    Original
    0.42
    fier
    0.42
    𝟭
    0.42
     Order
    0.41
    
    0.41
     venerable
    0.41
    POSITIVE LOGITS
     因為
    0.49
     doméstica
    0.47
     hazelnuts
    0.46
     طريقة
    0.45
     humedad
    0.45
     legumes
    0.44
     Porque
    0.43
     χρήση
    0.43
     زيادة
    0.43
     porque
    0.43
    Activations Density 0.000%

    No Known Activations