© 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. 33371
    Prev
    Next
    INDEX
    Explanations

    crime scene investigation

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

    terminology and scenes related to crime scene investigations and police work.

    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
     színes
    -0.98
     bőr
    -0.89
     Shetterly
    -0.81
    鵡
    -0.80
     hő
    -0.80
     folyam
    -0.79
    nowu
    -0.78
     recensement
    -0.77
     Âge
    -0.77
    Nomenclature
    -0.77
    POSITIVE LOGITS
     crime
    3.23
    crime
    2.44
     Crime
    2.22
    Crime
    2.22
     CRIME
    1.98
     scene
    1.91
     evidence
    1.65
    scene
    1.59
     CSI
    1.57
     scenes
    1.54
    Activations Density 0.018%

    No Known Activations