© 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. 167758
    Prev
    Next
    INDEX
    Explanations

    new format

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

    explaining why or options

    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
     パン
    0.49
     chubby
    0.49
     fortæ
    0.49
     विजिट
    0.48
     ガラス
    0.48
     berätt
    0.46
    спе
    0.46
    APAN
    0.46
    蝦
    0.45
    ಿಯು
    0.43
    POSITIVE LOGITS
     θ
    0.46
     widely
    0.44
     licensees
    0.44
     টেলিভিশন
    0.44
     ditches
    0.43
    ά
    0.41
    ចំនួន
    0.40
     electrolytic
    0.40
     ϕ
    0.40
     …,
    0.40
    Activations Density 0.001%

    No Known Activations