© 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. 99128
    Prev
    Next
    INDEX
    Explanations

    hate speech and hate crimes

    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
    iterran
    -1.00
    عاية
    -0.87
    我在
    -0.87
    iterrane
    -0.86
     frightening
    -0.86
    assertNull
    -0.84
    Intersect
    -0.83
    Mahon
    -0.82
    ppard
    -0.82
     faith
    -0.82
    POSITIVE LOGITS
     HATE
    2.00
     Hate
    1.90
     hate
    1.73
    hate
    1.71
    Hate
    1.59
     ненави
    1.37
     hates
    1.33
     hatred
    1.23
     hated
    1.23
     keben
    1.11
    Activations Density 0.036%

    No Known Activations