© 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. 153029
    Prev
    Next
    INDEX
    Explanations

    but also

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

    steps in processes

    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
     possibilidade
    0.49
     possibilità
    0.49
     możliwości
    0.48
     cadeia
    0.47
     terme
    0.47
    箬
    0.47
     réseau
    0.47
     extérieur
    0.46
     gambler
    0.46
     công
    0.46
    POSITIVE LOGITS
    Paused
    0.52
    Reduce
    0.49
    Eval
    0.49
     ลด
    0.48
    롤
    0.48
    Invalid
    0.48
    Evalu
    0.48
    Relatives
    0.47
    Meeting
    0.47
    UN
    0.46
    Activations Density 0.000%

    No Known Activations