© 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. 79089
    Prev
    Next
    INDEX
    Explanations

    giving evidence in court

    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
     учреждения
    -0.84
    Mash
    -0.75
     Congressman
    -0.70
     akár
    -0.69
    Cir
    -0.67
    Joke
    -0.66
    uds
    -0.66
     récupération
    -0.66
     использованием
    -0.65
     punctured
    -0.65
    POSITIVE LOGITS
     evidence
    4.19
    evidence
    3.33
    Evidence
    3.22
     Evidence
    3.09
     EVIDENCE
    2.72
     evidencia
    2.28
     evidences
    2.25
    证据
    2.05
    vidence
    1.91
     evid
    1.66
    Activations Density 0.020%

    No Known Activations