© 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. 34-GEMMASCOPE-RES-131K
    7. 92699
    Prev
    Next
    INDEX
    Explanations

    harm and damage

    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
     fotográfica
    -0.81
     erd
    -0.80
    Changed
    -0.80
     チップ
    -0.79
     auri
    -0.79
     Factbook
    -0.78
     nghị
    -0.78
     adequada
    -0.78
    跤
    -0.77
    Photon
    -0.76
    POSITIVE LOGITS
     harm
    6.03
     Harm
    4.03
    harm
    3.97
     harms
    3.89
     harmed
    3.77
    Harm
    3.67
     hurt
    3.63
     damage
    3.25
     harming
    3.13
     harmful
    2.83
    Activations Density 0.060%

    No Known Activations