© 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. 84068
    Prev
    Next
    INDEX
    Explanations

    Q: questions

    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
    唐揚げ
    -0.83
    appé
    -0.83
    Architect
    -0.81
    ătoare
    -0.81
    andal
    -0.79
    ɤ
    -0.78
    CED
    -0.77
    inste
    -0.76
    ⚽
    -0.76
     Architect
    -0.76
    POSITIVE LOGITS
     WWF
    1.01
     Taras
    0.88
    WWF
    0.84
     territories
    0.82
     promoters
    0.81
     refer
    0.76
    ﾞ
    0.75
    referer
    0.73
     leopard
    0.72
     Existe
    0.71
    Activations Density 0.023%

    No Known Activations