© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14976
    Prev
    Next
    INDEX
    Explanations

    torture and punishment

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

    punishment, torture, abuse

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

    violence and imprisonment

    np_max-act · claude-4-5-sonnetTriggered by @sk5695
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     हादसे
    0.49
     refuge
    0.47
     self
    0.46
     защи
    0.44
     müm
    0.43
     Flücht
    0.43
     захи
    0.42
     защиты
    0.42
    рата
    0.42
     അപകട
    0.42
    POSITIVE LOGITS
     torture
    1.05
     নির্যাতন
    0.86
     sadistic
    0.84
    拷
    0.82
     tortured
    0.82
     Tort
    0.80
    Tort
    0.80
    tort
    0.77
     TORT
    0.76
     tort
    0.75
    Activations Density 0.321%

    No Known Activations