© 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. 71866
    Prev
    Next
    INDEX
    Explanations

    if/else conditions

    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
     PUSTAKA
    -2.05
    Ꮞ
    -1.70
     şeyler
    -1.60
    曖昧さ
    -1.55
    袛
    -1.55
     ombro
    -1.54
    cazione
    -1.54
    なども
    -1.52
     
    -1.46
     şeyi
    -1.46
    POSITIVE LOGITS
     if
    2.06
     there
    1.77
    The
    1.70
     seems
    1.68
    There
    1.58
    {\
    1.54
    If
    1.54
     you
    1.51
    ,
    1.47
     from
    1.45
    Activations Density 0.009%

    No Known Activations