© 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. 6856
    Prev
    Next
    INDEX
    Explanations

    data points or observations

    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
     SEAT
    -0.84
     zee
    -0.80
    лько
    -0.79
     Felt
    -0.77
     Repr
    -0.75
    Recre
    -0.74
    在住
    -0.73
    Normdaten
    -0.73
     IOM
    -0.73
    TOY
    -0.73
    POSITIVE LOGITS
     observations
    4.63
     observation
    4.03
     Observations
    3.55
    observations
    3.52
    Observations
    3.50
    observation
    3.45
     Observation
    3.22
    Observation
    3.19
     наблю
    2.97
     observaciones
    2.97
    Activations Density 0.108%

    No Known Activations