© 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. 128577
    Prev
    Next
    INDEX
    Explanations

    Concordia, Rupert, sputtering, Passover

    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
    '
    -3.41
     If
    -2.81
    ON
    -2.55
     інших
    -2.34
     â
    -2.19
    羕
    -2.19
     anderen
    -2.13
     questi
    -2.11
     Their
    -2.08
     Initialise
    -2.03
    POSITIVE LOGITS
    〠
    2.69
    玧
    2.66
     柄
    2.53
    ჻
    2.47
    缡
    2.47
    
    2.45
    ౮
    2.41
    footnotesize
    2.36
    logiques
    2.33
    ECTOS
    2.33
    Activations Density 0.026%

    No Known Activations