© 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. 34-GEMMASCOPE-RES-131K
    7. 32377
    Prev
    Next
    INDEX
    Explanations

    pedo guy QAnon child abuse

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     immediate
    -0.73
    textInput
    -0.72
    Genial
    -0.71
     always
    -0.71
    样本
    -0.71
     scam
    -0.71
    AppSettings
    -0.71
     න
    -0.70
    feinander
    -0.70
     cousins
    -0.70
    POSITIVE LOGITS
     child
    1.00
     ped
    0.98
     ritual
    0.91
     rituals
    0.88
     Ritual
    0.86
     cannibal
    0.85
     pizza
    0.84
     trafficking
    0.83
    pedo
    0.83
     procurer
    0.81
    Activations Density 0.010%

    No Known Activations