© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 128174
    Prev
    Next
    INDEX
    Explanations

    in place or into effect

    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
     the
    -1.86
     écout
    -1.66
    s
    -1.66
    from
    -1.65
     of
    -1.64
    to
    -1.60
    e
    -1.59
    on
    -1.57
    for
    -1.56
    鱚
    -1.55
    POSITIVE LOGITS
     klokken
    1.74
     veckor
    1.65
    ASTM
    1.65
    zembro
    1.62
     hvem
    1.59
    erializer
    1.55
    moil
    1.54
    äť
    1.53
     sidste
    1.52
    罔
    1.52
    Activations Density 0.081%

    No Known Activations