© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107596
    Prev
    Next
    INDEX
    Explanations

    sexual harassment and assault

    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
     limpi
    -0.91
    を抱
    -0.91
    introdu
    -0.89
     sospe
    -0.82
     blatant
    -0.81
    严重的
    -0.81
     prevented
    -0.81
     prevention
    -0.81
    introduce
    -0.80
     mitigating
    -0.79
    POSITIVE LOGITS
     attack
    2.02
     targeting
    1.96
     attacking
    1.95
    attack
    1.87
     target
    1.80
     prey
    1.72
     Targeting
    1.70
    targeting
    1.66
     attacks
    1.63
     attacked
    1.60
    Activations Density 0.116%

    No Known Activations