© 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. 39604
    Prev
    Next
    INDEX
    Explanations

    Jacksonville truly / Articles Applying

    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
    and
    -2.14
     you
    -1.96
     where
    -1.95
    ";
    -1.86
    </u>
    -1.84
    e
    -1.82
    which
    -1.77
    if
    -1.71
     facendo
    -1.71
    」
    -1.70
    POSITIVE LOGITS
     yılında
    1.85
    𓆜
    1.79
    莠
    1.68
    荜
    1.65
    detek
    1.59
    神
    1.57
    脔
    1.55
     débris
    1.53
     naïve
    1.53
     hôtels
    1.52
    Activations Density 0.001%

    No Known Activations