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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118943
    Prev
    Next
    INDEX
    Explanations

    recent figures and statistics

    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
    szönöm
    -0.86
     chi̍t
    -0.81
    ව
    -0.77
    годні
    -0.76
    fällen
    -0.75
    ordnung
    -0.74
    Ռ
    -0.73
    bigli
    -0.73
     pequeño
    -0.72
    ोजना
    -0.72
    POSITIVE LOGITS
     figures
    4.44
    figures
    3.33
    Figures
    3.17
     statistics
    3.03
     Figures
    2.83
     data
    2.66
     FIGURES
    2.39
     latest
    2.25
     chiffres
    2.20
     figure
    2.17
    Activations Density 0.044%

    No Known Activations