© 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. 22-GEMMASCOPE-RES-131K
    7. 130490
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and problems

    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_22/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
    Ла
    -0.90
    tenham
    -0.86
    Все
    -0.86
    圩
    -0.85
     on
    -0.85
    Когда
    -0.84
    jaga
    -0.84
     Jeux
    -0.83
    ابن
    -0.81
    ußer
    -0.81
    POSITIVE LOGITS
     delightful
    0.91
     fabulous
    0.90
     sumptuous
    0.88
    ographers
    0.88
    weetie
    0.85
     astounding
    0.82
    alogen
    0.81
     Umständen
    0.81
    要知道
    0.80
     bayonet
    0.79
    Activations Density 0.054%

    No Known Activations