© 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. 85563
    Prev
    Next
    INDEX
    Explanations

    Rose names and places

    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
    塒
    -3.45
     they
    -2.81
     critically
    -2.47
    柺
    -2.47
    樒
    -2.41
    龗
    -2.39
    梣
    -2.33
    欉
    -2.33
     momentous
    -2.30
    ta
    -2.28
    POSITIVE LOGITS
    9
    2.56
     et
    2.41
     автомобили
    2.38
    ly
    2.25
    When
    2.19
    ``
    2.19
    3
    2.19
    ６
    2.19
    </h3>
    2.16
     Stornier
    2.13
    Activations Density 0.005%

    No Known Activations