© 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. 30767
    Prev
    Next
    INDEX
    Explanations

    telecommunication companies and numbers

    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
     '<?
    -0.84
     thar
    -0.82
    metido
    -0.78
    ゑ
    -0.75
    UAV
    -0.74
    みます
    -0.74
    に入れる
    -0.73
    kształ
    -0.73
     لتح
    -0.73
     fto
    -0.73
    POSITIVE LOGITS
     Sprint
    1.02
     AT
    0.98
     (
    0.96
     Bell
    0.95
    Sprint
    0.91
     Verizon
    0.90
    Bell
    0.85
     azeite
    0.84
     île
    0.84
    Chall
    0.81
    Activations Density 0.002%

    No Known Activations