© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 3709
    Prev
    Next
    INDEX
    Explanations

    of another person

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     சுற்றுச்சூழல்
    0.50
     अणुओं
    0.46
    കർ
    0.45
    ahui
    0.45
     Emissions
    0.44
    COU
    0.44
     pagine
    0.44
     विस्तृत
    0.43
    ﺙ
    0.43
     कृपया
    0.43
    POSITIVE LOGITS
     similar
    0.46
     入っ
    0.46
     jaunes
    0.46
     imid
    0.44
    DeleteItem
    0.43
     losing
    0.42
     analogous
    0.42
     ninh
    0.42
     juj
    0.42
     shear
    0.42
    Activations Density 0.000%

    No Known Activations