© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111833
    Prev
    Next
    INDEX
    Explanations

    investigating incidents

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

    content related to ongoing investigations, particularly in official or law enforcement contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    </h3>
    -1.33
    咂
    -1.26
    checklist
    -1.26
    showroom
    -1.22
     officielles
    -1.21
    ferien
    -1.19
    媖
    -1.19
    чего
    -1.19
     extérieures
    -1.19
    llavero
    -1.18
    POSITIVE LOGITS
     first
    1.45
    âtel
    1.30
     but
    1.26
    最早
    1.25
     continue
    1.22
     subsequent
    1.20
     hoffe
    1.20
    UNRELATED
    1.20
     others
    1.20
     there
    1.18
    Activations Density 0.040%

    No Known Activations