© 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. 170704
    Prev
    Next
    INDEX
    Explanations

    journal cites and publications

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

    exploring desires and refusing

    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
     rythme
    0.53
    ил
    0.50
    ेशंस
    0.49
     unpredictable
    0.48
     rhythm
    0.47
     Attraction
    0.47
    ๚
    0.47
    clickView
    0.47
    猞
    0.47
    ඓ
    0.47
    POSITIVE LOGITS
     Öff
    0.50
     Thiết
    0.50
     Ajoutez
    0.50
     Bericht
    0.49
     Verhalten
    0.48
    STAR
    0.48
     Öğ
    0.47
    Fernando
    0.47
    Ż
    0.47
     Zusammen
    0.46
    Activations Density 0.001%

    No Known Activations