© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 2156
    Prev
    Next
    INDEX
    Explanations

    texture and visual descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ยืน
    0.69
    දි
    0.62
    一脸
    0.61
    重建
    0.61
     Mayıs
    0.61
    㚣
    0.60
     objetivos
    0.60
    Snapped
    0.60
    僖
    0.59
     मुसीबत
    0.59
    POSITIVE LOGITS
     texture
    2.09
     textures
    2.01
     Texture
    1.80
     textured
    1.76
    texture
    1.74
    Texture
    1.68
    textures
    1.65
     textura
    1.64
     textural
    1.62
     тексту
    1.55
    Activations Density 0.709%

    No Known Activations