© 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. 108904
    Prev
    Next
    INDEX
    Explanations

    given names followed by surnames

    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
     Blame
    -0.79
    lelő
    -0.79
    tales
    -0.76
    ненный
    -0.75
    تمام
    -0.75
    Далее
    -0.74
    なぁ
    -0.73
    blobs
    -0.72
     spiro
    -0.71
     rubro
    -0.71
    POSITIVE LOGITS
    ISTE
    0.78
     Völ
    0.75
     RATES
    0.73
     описание
    0.73
    COMPLETE
    0.72
    ⬤
    0.70
    SELECTION
    0.69
     them
    0.69
     öz
    0.68
    ributing
    0.68
    Activations Density 0.015%

    No Known Activations