© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 31031
    Prev
    Next
    INDEX
    Explanations

    avoidable deaths and suffering

    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
    hian
    -0.92
    めた
    -0.83
    あく
    -0.82
     broma
    -0.82
     bieden
    -0.81
    icato
    -0.80
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.79
     gonz
    -0.79
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.79
    さすがに
    -0.79
    POSITIVE LOGITS
     unnecessary
    3.48
     avoidable
    3.27
     preventable
    2.89
     unnecessarily
    2.81
     needless
    2.70
     needlessly
    2.64
     inneces
    1.88
     needn
    1.59
    preven
    1.58
     Avoid
    1.41
    Activations Density 0.091%

    No Known Activations