© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129276
    Prev
    Next
    INDEX
    Explanations

    ggplot `aes` or UI metadata

    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
     هستند
    -1.11
     alent
    -1.07
    𒊹
    -1.05
     viewWillAppear
    -1.05
     fontWeight
    -1.04
    щность
    -1.02
    parfum
    -1.02
     verranno
    -1.01
     whichever
    -1.00
     rapat
    -0.99
    POSITIVE LOGITS
    Você
    1.12
    You
    1.04
    symmetry
    0.98
    ₤
    0.92
    It
    0.90
    หน้าน
    0.89
    ISTAN
    0.89
    この
    0.88
    rédients
    0.88
     tudi
    0.87
    Activations Density 0.001%

    No Known Activations