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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12339
    Prev
    Next
    INDEX
    Explanations

    career and life 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
     or
    -2.06
     for
    -1.88
     our
    -1.59
     then
    -1.52
     on
    -1.52
     to
    -1.48
     so
    -1.47
     this
    -1.46
     that
    -1.45
     if
    -1.42
    POSITIVE LOGITS
    particularly
    1.81
     notamment
    1.38
    frequently
    1.35
    especially
    1.34
    фии
    1.27
     ESPEC
    1.26
     VIDEOS
    1.25
     zejména
    1.25
     gyak
    1.23
     โดย
    1.23
    Activations Density 0.103%

    No Known Activations