© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 49415
    Prev
    Next
    INDEX
    Explanations

    framing issues

    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
    Not in Any Lists

    No Comments

    Negative Logits
     potencial
    0.52
    ස
    0.51
     സമയ
    0.50
     deformations
    0.48
    ي
    0.47
    અ
    0.47
     possível
    0.46
     những
    0.45
    අ
    0.44
     posible
    0.43
    POSITIVE LOGITS
    ↵↵↵
    0.44
    idiendo
    0.44
     Sees
    0.42
     AI
    0.42
     Ai
    0.42
     Quite
    0.42
    xymatrix
    0.42
              
    0.42
      
    0.41
     Bona
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.