© 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. 10-GEMMASCOPE-RES-131K
    7. 129462
    Prev
    Next
    INDEX
    Explanations

    timur, маленьких

    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_10/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
     What
    -2.36
    ⩤
    -2.23
     murky
    -2.13
     unwavering
    -2.13
    鴞
    -2.05
     glittering
    -2.02
    彼は
    -2.00
     However
    -2.00
     añad
    -1.93
     как
    -1.87
    POSITIVE LOGITS
    3
    3.34
    2
    3.00
    4
    2.94
    1
    2.70
    5
    2.48
    7
    2.44
    8
    2.36
     timur
    2.33
    6
    2.31
     маленьких
    2.11
    Activations Density 0.029%

    No Known Activations