© 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. 229719
    Prev
    Next
    INDEX
    Explanations

    phone numbers and version

    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
    晔
    0.48
    ?
    0.46
    偉
    0.44
    始めて
    0.44
     karo
    0.44
     gigantes
    0.41
    题
    0.41
     gigantic
    0.41
     warden
    0.40
    警察
    0.40
    POSITIVE LOGITS
     ဘ
    0.47
     ព
    0.46
    тиви
    0.46
     Ви
    0.44
    andra
    0.43
    ıştır
    0.43
    üge
    0.43
     ಹೆಸರು
    0.42
     ऑ
    0.42
    astrar
    0.42
    Activations Density 0.000%

    No Known Activations