© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14472
    Prev
    Next
    INDEX
    Explanations

    phone number extensions

    np_acts-logits-general · gemini-2.5-flash-lite

    6 followed by hyphen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     其中
    0.45
    fillStyle
    0.44
    <unused742>
    0.44
     、,
    0.42
    on
    0.42
    <unused994>
    0.42
    <unused430>
    0.42
     。,
    0.41
    ಮೆ
    0.41
    ーン
    0.41
    POSITIVE LOGITS
     HubSpot
    0.43
     Extensions
    0.42
     Bereiche
    0.39
     сообщения
    0.38
     ६
    0.38
     सुमारे
    0.38
     Kuh
    0.38
     Solver
    0.38
     Roadster
    0.38
     for
    0.37
    Activations Density 0.061%

    No Known Activations