© 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. 22149
    Prev
    Next
    INDEX
    Explanations

    court documents and dates

    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
     without
    -1.60
    șit
    -1.45
     بدون
    -1.45
     ohne
    -1.41
     در
    -1.40
     we
    -1.34
    r
    -1.33
     với
    -1.31
    licante
    -1.31
    vu
    -1.27
    POSITIVE LOGITS
     about
    2.72
     they
    1.55
    cestor
    1.42
     which
    1.41
     then
    1.41
     how
    1.39
     regarding
    1.28
    ֶּ
    1.27
     concerning
    1.24
     Propiedad
    1.22
    Activations Density 0.166%

    No Known Activations