© 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. 22-GEMMASCOPE-RES-131K
    7. 36158
    Prev
    Next
    INDEX
    Explanations

    canceled or postponed events

    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_22/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
     zvíř
    -0.78
    終於
    -0.76
    mittent
    -0.75
    Created
    -0.75
     وبعد
    -0.73
    beitung
    -0.73
     vanden
    -0.73
    integrating
    -0.73
    终于
    -0.72
    onauts
    -0.71
    POSITIVE LOGITS
     planned
    2.23
     scheduled
    2.20
     intended
    1.59
     geplant
    1.58
     proposed
    1.55
     slated
    1.47
     anticipated
    1.45
    planned
    1.45
    scheduled
    1.43
     expected
    1.40
    Activations Density 0.091%

    No Known Activations