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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 90343
    Prev
    Next
    INDEX
    Explanations

    weight and related measurements

    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
     государ
    -0.73
    [['
    -0.72
     покри
    -0.71
     glutathione
    -0.70
     incurred
    -0.69
     münchen
    -0.68
    Claims
    -0.68
    torio
    -0.67
    orkan
    -0.66
     folklor
    -0.66
    POSITIVE LOGITS
     Weight
    1.23
    Weight
    1.09
    weight
    1.09
     weight
    1.09
     heavier
    1.06
     Gewichts
    1.05
    weig
    1.03
     Weigh
    1.03
     heaviest
    1.00
    weights
    1.00
    Activations Density 0.008%

    No Known Activations