© 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. 109082
    Prev
    Next
    INDEX
    Explanations

    javascript code imports

    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
     мысль
    -0.83
     چرا
    -0.80
    +#+
    -0.77
    roth
    -0.77
     Rotary
    -0.77
    歯
    -0.77
    scaled
    -0.75
     Khalid
    -0.75
     Cards
    -0.75
     impeller
    -0.74
    POSITIVE LOGITS
    ンバー
    0.86
     donut
    0.85
    orkshire
    0.84
    ("."
    0.83
    Grá
    0.83
    anj
    0.83
     misure
    0.82
    argli
    0.82
    empre
    0.82
     azioni
    0.81
    Activations Density 0.005%

    No Known Activations