© 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. 44515
    Prev
    Next
    INDEX
    Explanations

    start or test actions

    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
     through
    -2.31
     on
    -1.91
     The
    -1.85
     than
    -1.78
     for
    -1.74
     like
    -1.57
     as
    -1.52
     via
    -1.52
    The
    -1.51
     V
    -1.50
    POSITIVE LOGITS
     geel
    1.71
     that
    1.61
    
    1.55
     telt
    1.51
     noten
    1.51
     it
    1.50
     cursus
    1.48
    珰
    1.48
     kalender
    1.46
    ſſi
    1.44
    Activations Density 0.115%

    No Known Activations