© 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. 170705
    Prev
    Next
    INDEX
    Explanations

    black colored, Missouri learners, judge, body likes, cause to, we bought, Silver w

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

    build quality

    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
    ↵
    0.70
       
    0.57
            
    0.55
    0.49
    క్కు
    0.46
        
    0.44
    ↵↵
    0.43
     TypeToken
    0.43
           
    0.43
    General
    0.42
    POSITIVE LOGITS
    evolving
    0.55
     விண்ண
    0.53
     ιστο
    0.50
    <unused424>
    0.50
    opting
    0.49
     σκ
    0.49
    Gosudarstvennyj
    0.49
    elit
    0.48
    <unused276>
    0.48
    <unused633>
    0.47
    Activations Density 0.000%

    No Known Activations