© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129685
    Prev
    Next
    INDEX
    Explanations

    may be to indicate possibility

    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
     then
    -1.16
     actually
    -1.05
     already
    -1.04
     kaffe
    -0.98
     really
    -0.95
     almost
    -0.93
     only
    -0.92
     enough
    -0.91
     too
    -0.91
     now
    -0.91
    POSITIVE LOGITS
     may
    1.77
     algunas
    1.58
     algunos
    1.57
     ممکن
    1.47
     некоторых
    1.40
     niektó
    1.39
     mungkin
    1.35
     alcuni
    1.33
     bazı
    1.32
     niektor
    1.30
    Activations Density 0.068%

    No Known Activations