© 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. 171956
    Prev
    Next
    INDEX
    Explanations

    Zayn Malik

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

    avoid negatives and specify clearly

    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
    Smile
    0.56
    Pause
    0.51
    Already
    0.51
    Aye
    0.49
    ANY
    0.48
    inters
    0.47
    C
    0.46
    already
    0.46
    Shopping
    0.45
    Medi
    0.45
    POSITIVE LOGITS
     établissements
    0.53
    肐
    0.53
     eléctrico
    0.50
     nervioso
    0.48
    точной
    0.47
     Piotr
    0.47
    的名
    0.46
    據
    0.46
     departamentos
    0.46
     Dudley
    0.45
    Activations Density 0.000%

    No Known Activations