© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108054
    Prev
    Next
    INDEX
    Explanations

    code comments and declarations

    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
     Chil
    -0.73
    ANTES
    -0.72
     सी
    -0.70
     Hist
    -0.70
    flatMap
    -0.68
     absch
    -0.68
    짤
    -0.66
     Privat
    -0.66
    Bandwidth
    -0.66
    щина
    -0.65
    POSITIVE LOGITS
     difficulty
    1.16
     dificultad
    1.05
    difficulty
    1.02
     Difficulty
    0.98
     difficulté
    0.95
     dificuldade
    0.93
     dificultades
    0.88
     difficoltà
    0.85
     Difficult
    0.82
     hexadecimal
    0.82
    Activations Density 0.004%

    No Known Activations