© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 108810
    Prev
    Next
    INDEX
    Explanations

    ending phrases

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

    contribute to, intensifies, enhancing natural

    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
    Negative Logits
    Prz
    0.50
    Quit
    0.45
    Princip
    0.45
     automatis
    0.44
    Quel
    0.43
     Kirkpatrick
    0.43
     Schulz
    0.42
    ቋ
    0.42
    Ges
    0.42
     defect
    0.41
    POSITIVE LOGITS
     polyhedron
    0.49
    usic
    0.49
     சிவப்பு
    0.49
    बॉक्स
    0.47
     लेंस
    0.47
     நூற்றாண்டின்
    0.46
     крас
    0.46
     أمس
    0.46
     کیف
    0.46
    㑼
    0.46
    Activations Density 0.001%

    No Known Activations