© 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. 100005
    Prev
    Next
    INDEX
    Explanations

    is followed by properties

    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
     but
    -1.77
     ของ
    -1.70
     princípios
    -1.69
     respectivos
    -1.64
    隂
    -1.63
     alkoholu
    -1.57
     momentary
    -1.56
     conocimientos
    -1.55
     několika
    -1.55
     to
    -1.53
    POSITIVE LOGITS
     any
    2.13
     it
    2.08
    2
    1.87
     an
    1.82
     a
    1.82
     if
    1.80
     something
    1.78
     this
    1.77
     your
    1.73
     somebody
    1.66
    Activations Density 0.014%

    No Known Activations