© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5906
    Prev
    Next
    INDEX
    Explanations

    surface features and texture

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

    surface texture and shape irregularities

    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_53_width_65k_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
    狧
    0.44
     Rotten
    0.44
     वेळा
    0.41
    نوان
    0.41
     اكس
    0.40
     queryset
    0.40
    ادری
    0.40
    잽
    0.39
     cadre
    0.39
     blockbuster
    0.39
    POSITIVE LOGITS
     grooves
    2.17
     ridges
    2.02
     groove
    1.80
    凹
    1.77
     ridge
    1.67
     bumps
    1.66
     notches
    1.47
     depressions
    1.44
     bumpy
    1.43
     groves
    1.41
    Activations Density 0.232%

    No Known Activations