© 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. 72757
    Prev
    Next
    INDEX
    Explanations

    access, amounts, associated

    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
    ch
    0.58
            
    0.56
      
    0.54
     TS
    0.54
           
    0.53
     its
    0.53
     AL
    0.52
    al
    0.52
     TR
    0.51
     IL
    0.51
    POSITIVE LOGITS
    睾
    0.61
    峦
    0.51
    筋肉
    0.51
    强者
    0.51
    委員會
    0.51
    箓
    0.51
    ൮
    0.50
    膂
    0.48
     резко
    0.48
    zentration
    0.48
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.