© 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. 86740
    Prev
    Next
    INDEX
    Explanations

    code references with identifiers

    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
    itaji
    -0.79
    Več
    -0.78
     relegation
    -0.75
     Zwiebel
    -0.73
    šti
    -0.72
     WQS
    -0.71
    うーん
    -0.70
    rower
    -0.70
    髄
    -0.69
    tgz
    -0.69
    POSITIVE LOGITS
     scale
    1.43
    scale
    1.31
    Scale
    1.24
    SCALE
    1.21
     scaling
    1.21
     width
    1.20
     Scale
    1.12
     Scales
    1.09
     scales
    1.06
     scaled
    0.98
    Activations Density 0.002%

    No Known Activations