© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48215
    Prev
    Next
    INDEX
    Explanations

    coding and technical terms

    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
    Ascending
    -0.81
     AVR
    -0.71
    EXPAND
    -0.70
     residues
    -0.68
     petani
    -0.67
    Brit
    -0.67
     GmbH
    -0.67
     elm
    -0.66
     expediente
    -0.65
     tubules
    -0.65
    POSITIVE LOGITS
     éclat
    0.69
    interpre
    0.69
     борьбы
    0.65
     Boom
    0.65
     glass
    0.64
     Dunbar
    0.64
    etate
    0.64
     解
    0.63
     prima
    0.63
     bipolar
    0.63
    Activations Density 0.058%

    No Known Activations