© 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. 99675
    Prev
    Next
    INDEX
    Explanations

    threats and coercion

    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
     decorativa
    -0.83
    modifier
    -0.80
     Honig
    -0.79
     kaban
    -0.78
     Seil
    -0.77
     culturali
    -0.77
     mengakui
    -0.76
    问道
    -0.75
     laby
    -0.74
    oghi
    -0.74
    POSITIVE LOGITS
     threats
    3.19
     threat
    2.72
    threat
    2.56
     threaten
    2.45
     threatened
    2.45
     threatening
    2.44
     Threats
    2.22
     угро
    2.19
    Threat
    2.14
     Threat
    2.13
    Activations Density 0.027%

    No Known Activations