© 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. 10-GEMMASCOPE-RES-131K
    7. 41099
    Prev
    Next
    INDEX
    Explanations

    future plans or intentions

    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_10/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
     archaic
    -1.95
    就连
    -1.72
     miembros
    -1.67
     ň
    -1.66
    étaires
    -1.66
    ⬈
    -1.65
    *{-
    -1.64
     visse
    -1.64
    CodeAttribute
    -1.64
     این
    -1.64
    POSITIVE LOGITS
     all
    1.96
     longtime
    1.96
     just
    1.93
     more
    1.85
     not
    1.84
     adding
    1.83
     after
    1.81
     suggested
    1.77
     was
    1.75
     any
    1.72
    Activations Density 0.063%

    No Known Activations