© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78508
    Prev
    Next
    INDEX
    Explanations

    such as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    除非
    -0.84
    Ա
    -0.82
     sagrada
    -0.81
     steder
    -0.79
    立った
    -0.77
     forstå
    -0.76
    dali
    -0.75
    except
    -0.75
    Źródło
    -0.75
    śli
    -0.74
    POSITIVE LOGITS
     such
    0.88
     berbagai
    0.79
     sudoku
    0.79
     سات
    0.76
    色んな
    0.75
    JsonResponse
    0.75
     leit
    0.75
     Ebene
    0.75
     astfel
    0.75
     такой
    0.74
    Activations Density 0.001%

    No Known Activations