© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1951
    Prev
    Next
    INDEX
    Explanations

    evidence testing, audio authentication, DNA verification

    np_acts-logits-general · gemini-2.5-flash-lite

    terminology and concepts related to forensic science, evidence collection, and laboratory analysis.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    cyto
    -0.78
     cyto
    -0.76
     unfriendly
    -0.75
    ddha
    -0.75
    lň
    -0.73
     Investigations
    -0.71
     sırasında
    -0.71
    jabat
    -0.71
    ׂ
    -0.70
     Aquí
    -0.69
    POSITIVE LOGITS
     comparison
    1.09
     presump
    0.98
     comparisons
    0.93
     questioned
    0.90
     recovered
    0.85
     confronto
    0.83
    exemplar
    0.83
     Matches
    0.82
     exemplar
    0.79
    Matches
    0.77
    Activations Density 0.021%

    No Known Activations