© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110910
    Prev
    Next
    INDEX
    Explanations

    ordering subjects to comply

    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
     имму
    -0.84
     trasc
    -0.84
     tigre
    -0.82
     doktor
    -0.81
    FOTOS
    -0.80
    Flaming
    -0.79
    tiefel
    -0.78
    defender
    -0.77
     dramat
    -0.76
     seno
    -0.76
    POSITIVE LOGITS
     consented
    0.86
     consent
    0.83
     Monte
    0.81
    kt
    0.80
     compliance
    0.80
     HK
    0.79
     asked
    0.78
     advised
    0.78
     Lovely
    0.77
     Smith
    0.76
    Activations Density 0.015%

    No Known Activations