© 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. 34-GEMMASCOPE-RES-131K
    7. 57081
    Prev
    Next
    INDEX
    Explanations

    res judicata, collateral estoppel, law of the case

    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_34/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
     multicolore
    -1.19
     EXCELL
    -1.13
     Dinas
    -1.13
     MAKING
    -1.13
     siè
    -1.11
     pernic
    -1.09
     bricola
    -1.09
    acions
    -1.09
    믐
    -1.09
     courriel
    -1.06
    POSITIVE LOGITS
     pre
    1.22
     so
    1.18
     first
    1.17
     take
    1.16
     using
    1.16
     modified
    1.15
     implied
    1.14
     just
    1.13
     taking
    1.13
     good
    1.12
    Activations Density 0.080%

    No Known Activations