© 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. 48902
    Prev
    Next
    INDEX
    Explanations

    complaints and denouncements

    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
    ecutable
    -0.96
    🥿
    -0.73
     примі
    -0.71
     faulty
    -0.71
     thời
    -0.71
    vanje
    -0.71
    łasz
    -0.70
     Aufwand
    -0.70
    oscopy
    -0.69
    Approve
    -0.69
    POSITIVE LOGITS
     denounced
    3.47
     denounce
    3.41
     denunci
    3.19
     den
    2.89
     denuncia
    2.55
     dénon
    2.52
     Den
    2.36
     denuncias
    2.28
     DEN
    2.20
    Den
    2.13
    Activations Density 0.022%

    No Known Activations