© 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. 22-GEMMASCOPE-RES-131K
    7. 33306
    Prev
    Next
    INDEX
    Explanations

    Illinois and California court citations

    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_22/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
    ७
    -1.09
    crollView
    -1.09
     шокола
    -1.08
    つづく
    -1.07
    🌾
    -1.04
    OURCE
    -1.03
     <?=
    -1.02
    に於
    -1.01
    他有
    -1.00
    dengan
    -1.00
    POSITIVE LOGITS
    .
    1.20
     examples
    1.20
    न्दर्भ
    1.19
     pesquisas
    1.06
     тях
    1.05
     see
    1.05
    頂きました
    1.02
    ੨
    1.01
     either
    1.00
    Література
    1.00
    Activations Density 0.002%

    No Known Activations