© 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. 22-GEMMASCOPE-RES-131K
    7. 66161
    Prev
    Next
    INDEX
    Explanations

    names followed by context

    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_22/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
     and
    -1.07
     November
    -1.06
    力で
    -1.05
    ınız
    -0.99
    عين
    -0.98
     October
    -0.98
     Ľ
    -0.98
    gı
    -0.98
    ехать
    -0.97
    ınızı
    -0.96
    POSITIVE LOGITS
     chaînes
    1.03
     ざ
    1.02
    hilation
    1.02
    wasn
    1.00
     HYDRA
    1.00
     éléments
    0.99
     radioButton
    0.98
     ALTO
    0.98
    atin
    0.97
    could
    0.96
    Activations Density 0.000%

    No Known Activations