© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 43135
    Prev
    Next
    INDEX
    Explanations

    athletic combine measurements

    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
     их
    -1.39
    莛
    -1.36
    ྄
    -1.31
    着她
    -1.24
     mapas
    -1.23
     ahora
    -1.23
     немає
    -1.20
    %"),
    -1.19
    镡
    -1.17
    Alors
    -1.16
    POSITIVE LOGITS
     should
    1.23
     that
    1.12
    erebbe
    1.10
     for
    1.09
     the
    1.08
     merusak
    1.07
     if
    1.05
     pernah
    0.99
     providing
    0.99
     Mengen
    0.99
    Activations Density 0.044%

    No Known Activations