© 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. 54081
    Prev
    Next
    INDEX
    Explanations

    found or discovered

    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
     for
    -1.83
     to
    -1.52
     seen
    -1.34
     seeing
    -1.12
    seen
    -1.11
    observed
    -1.01
     щоб
    -0.98
     unseen
    -0.96
    olle
    -0.93
     gesehen
    -0.92
    POSITIVE LOGITS
     buried
    1.23
     lors
    1.20
     thanks
    1.12
     hiding
    1.11
     near
    1.06
     hidden
    1.05
     while
    1.05
     during
    1.02
     vinaigre
    1.02
     whilst
    1.01
    Activations Density 0.099%

    No Known Activations