© 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. 129115
    Prev
    Next
    INDEX
    Explanations

    não or nothing

    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
    이고
    -2.84
     annoy
    -2.66
    他的
    -2.66
     сотрудники
    -2.50
    D
    -2.47
    q
    -2.45
    k
    -2.45
    B
    -2.42
    V
    -2.41
    h
    -2.38
    POSITIVE LOGITS
    镡
    2.55
    .
    2.38
     consideradas
    2.27
    痦
    2.19
     esperando
    2.09
    随之
    2.09
     twa
    2.08
     ott
    2.06
    灕
    2.06
     itſelf
    2.05
    Activations Density 0.001%

    No Known Activations