© 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. 36078
    Prev
    Next
    INDEX
    Explanations

    expressing possibility or uncertainty

    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
    usually
    -1.49
    definitely
    -1.48
    obviously
    -1.46
    probably
    -1.46
     ſou
    -1.43
     viſ
    -1.39
    certainly
    -1.38
    preferably
    -1.38
     tampaknya
    -1.37
     varier
    -1.34
    POSITIVE LOGITS
     just
    1.97
     even
    1.81
     may
    1.63
     have
    1.48
     also
    1.47
     simply
    1.42
     still
    1.34
    ",
    1.34
     already
    1.32
     more
    1.30
    Activations Density 0.036%

    No Known Activations