© 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. 10-GEMMASCOPE-RES-131K
    7. 84735
    Prev
    Next
    INDEX
    Explanations

    extortion and blackmail demands

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

    The neuron detects mentions of coercive crimes—especially “extort(ion)” and “blackmail” (and related forms like “racketeering”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     "}";
    -2.27
     doubtnut
    -2.00
     unga
    -1.95
     rancho
    -1.88
     romero
    -1.88
     GOtt
    -1.88
    buttonShape
    -1.87
     encompassed
    -1.85
     said
    -1.84
     prado
    -1.84
    POSITIVE LOGITS
    ↵
    2.61
    0
    2.08
    ioren
    1.95
     "
    1.91
    “
    1.84
     tocó
    1.80
     muchos
    1.72
    ."
    1.66
     kleinen
    1.65
    */
    1.63
    Activations Density 0.004%

    No Known Activations