© 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. 38074
    Prev
    Next
    INDEX
    Explanations

    Silence of the Lambs

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

    The neuron fires on mentions of “The Silence of the Lambs” (and its characters like Hannibal Lecter and Clarice).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     power
    -1.07
     Power
    -0.96
    Power
    -0.93
    power
    -0.82
     overhead
    -0.81
    bbage
    -0.78
     wires
    -0.70
    overhead
    -0.70
    装飾
    -0.69
     GLP
    -0.68
    POSITIVE LOGITS
     Hannibal
    1.62
     cannibal
    1.26
     Lec
    1.23
     Silence
    1.18
     Clar
    1.10
    Silence
    1.06
    Han
    1.05
    nibal
    0.94
     silence
    0.92
     Hann
    0.92
    Activations Density 0.010%

    No Known Activations