© 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. 78412
    Prev
    Next
    INDEX
    Explanations

    court case 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_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
    Colleen
    -0.84
     deutschen
    -0.78
    acuzzi
    -0.75
     Colgate
    -0.75
     tế
    -0.74
    ampunk
    -0.74
    zzb
    -0.73
     dico
    -0.72
     pouvaient
    -0.72
    atal
    -0.72
    POSITIVE LOGITS
    Wiel
    0.89
     Wiel
    0.76
    KLE
    0.73
    JOIN
    0.72
    攀
    0.71
    Ⅸ
    0.71
    wasan
    0.71
    Seeds
    0.71
    Higgs
    0.71
    かれ
    0.70
    Activations Density 0.042%

    No Known Activations