© 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. 72933
    Prev
    Next
    INDEX
    Explanations

    numbers and years

    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
    ложений
    -1.16
    //-->
    -1.15
    ctrica
    -1.05
     היתה
    -1.03
     we
    -0.99
     храм
    -0.97
    `:
    -0.96
    锻
    -0.96
    olyte
    -0.93
    ///
    -0.93
    POSITIVE LOGITS
    conto
    1.09
    <sup>
    1.08
     čier
    1.07
    dolu
    1.03
     любых
    1.02
    畿
    1.00
     žal
    1.00
     viewing
    0.99
     africaine
    0.99
    usure
    0.98
    Activations Density 0.105%

    No Known Activations