© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 28188
    Prev
    Next
    INDEX
    Explanations

    contrast and seeking information

    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
     phénomène
    -0.95
     centavos
    -0.89
    nl
    -0.87
    Евгений
    -0.85
     nmax
    -0.84
    andal
    -0.82
    ñal
    -0.81
     have
    -0.81
    Brasil
    -0.80
    als
    -0.80
    POSITIVE LOGITS
     but
    6.56
     nhưng
    3.50
     แต่
    3.38
    but
    3.03
     But
    2.95
     αλλά
    2.86
    But
    2.81
     ولكن
    2.78
    但是
    2.77
     tetapi
    2.73
    Activations Density 0.221%

    No Known Activations