© 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. 34-GEMMASCOPE-RES-131K
    7. 58015
    Prev
    Next
    INDEX
    Explanations

    numbers following certain words

    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
     примерно
    -1.43
    Approximately
    -1.38
     Approximately
    -1.34
    Hundreds
    -1.22
     approximately
    -1.21
    は約
    -1.18
     varias
    -1.13
     hundreds
    -1.11
    Several
    -1.10
     berbagai
    -1.07
    POSITIVE LOGITS
     two
    3.80
     one
    3.45
     three
    3.09
     four
    2.75
     five
    2.67
    two
    2.48
     six
    2.27
     seven
    2.27
    three
    2.22
     één
    2.19
    Activations Density 0.133%

    No Known Activations