© 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. 108174
    Prev
    Next
    INDEX
    Explanations

    technical institutions or specific entities

    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
     специ
    -0.77
     standardization
    -0.76
    VH
    -0.74
     taas
    -0.70
     counselling
    -0.68
     bezpośrednio
    -0.66
     pace
    -0.65
    收拾
    -0.65
     bersih
    -0.64
     VH
    -0.64
    POSITIVE LOGITS
     Lisbon
    0.80
    READ
    0.76
     conexão
    0.75
     hippocampus
    0.73
    ramento
    0.72
    Widths
    0.71
    manuel
    0.70
    ecciones
    0.70
    heira
    0.69
     MSW
    0.69
    Activations Density 0.011%

    No Known Activations