© 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. 14670
    Prev
    Next
    INDEX
    Explanations

    decoration and visualization

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

    branding and visualization

    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
     incompet
    0.47
     القيام
    0.47
     लाहि
    0.46
     burdensome
    0.43
    gado
    0.43
     facilita
    0.43
     maneu
    0.42
    劧
    0.42
    nout
    0.42
     అన్ని
    0.42
    POSITIVE LOGITS
     décoration
    0.81
    装饰
    0.80
     adorn
    0.76
     iconography
    0.75
    Decoration
    0.73
     Visualization
    0.72
     visualizing
    0.72
     Decoration
    0.71
     decoration
    0.71
     decorative
    0.70
    Activations Density 0.274%

    No Known Activations