© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40079
    Prev
    Next
    INDEX
    Explanations

    county seat is

    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
    靱
    -1.83
     their
    -1.68
     campesinos
    -1.66
    éndose
    -1.66
     each
    -1.66
    或
    -1.66
     دخترانه
    -1.65
     every
    -1.63
    暧
    -1.62
     during
    -1.59
    POSITIVE LOGITS
     of
    1.80
    if
    1.73
     didn
    1.65
     если
    1.57
     doesn
    1.52
    ma
    1.49
     don
    1.48
     отдых
    1.48
    ver
    1.47
    ja
    1.45
    Activations Density 0.471%

    No Known Activations