© 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. 10-GEMMASCOPE-RES-131K
    7. 15249
    Prev
    Next
    INDEX
    Explanations

    cellular network infrastructure

    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
     changes
    -1.75
     these
    -1.42
     osallist
    -1.41
     changing
    -1.40
    audiovisuel
    -1.34
     changed
    -1.33
    _'.$
    -1.33
     często
    -1.29
     často
    -1.27
    ]^{-
    -1.27
    POSITIVE LOGITS
     sangat
    1.31
    тся
    1.22
    sehr
    1.19
     commencé
    1.19
    ዣ
    1.17
    SizeF
    1.16
     WHO
    1.14
     ANOTHER
    1.13
    嵛
    1.13
     prakti
    1.12
    Activations Density 0.128%

    No Known Activations