© 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. 128589
    Prev
    Next
    INDEX
    Explanations

    255

    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
    {
    -2.94
     intenta
    -2.39
    但他
    -2.06
    硨
    -2.00
    re
    -1.96
    ",
    -1.88
    '
    -1.88
     incorpora
    -1.83
     recibirá
    -1.83
    みよう
    -1.83
    POSITIVE LOGITS
    ఞ
    2.63
    ಞ
    2.25
     vorliegenden
    2.17
    䛗
    2.14
     でも
    2.13
    ribue
    2.13
    IALE
    2.06
    焄
    2.05
    CurtirCurtir
    2.03
     Когда
    1.99
    Activations Density 0.002%

    No Known Activations