© 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. 34-GEMMASCOPE-RES-131K
    7. 47445
    Prev
    Next
    INDEX
    Explanations

    Insert a parameter

    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_34/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
     Había
    -0.91
     Muitos
    -0.91
     Algunos
    -0.89
     Aún
    -0.85
     Talvez
    -0.84
     والأ
    -0.84
     Tampoco
    -0.82
     Allí
    -0.81
     Simplemente
    -0.81
     Estaba
    -0.80
    POSITIVE LOGITS
     A
    3.97
    A
    2.53
    getA
    1.70
     А
    1.67
    a
    1.54
    Ａ
    1.54
     a
    1.35
     أ
    1.18
    ａ
    1.15
     а
    1.13
    Activations Density 0.351%

    No Known Activations