© 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. 39038
    Prev
    Next
    INDEX
    Explanations

    news headlines

    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
    0
    -2.19
    ra
    -2.11
    h
    -2.08
     
    -2.05
     is
    -2.03
    n
    -2.02
    us
    -1.93
    ta
    -1.88
    ti
    -1.78
    ma
    -1.77
    POSITIVE LOGITS
     and
    2.41
     such
    2.02
     traktor
    1.88
    鈮
    1.86
    㩒
    1.79
    amaño
    1.74
    )),
    1.70
    indari
    1.70
    ครื่อง
    1.66
    轳
    1.64
    Activations Density 0.034%

    No Known Activations