© 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. 72699
    Prev
    Next
    INDEX
    Explanations

    conditional logic and code

    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
     célè
    -1.22
     discuter
    -1.13
     hés
    -1.13
     parfüm
    -1.09
     rése
    -1.09
    ącz
    -1.09
     flotte
    -1.08
     gagne
    -1.05
     écl
    -1.05
     maniere
    -1.02
    POSITIVE LOGITS
     PCR
    0.99
    ulipas
    0.97
     if
    0.93
     G
    0.93
    zina
    0.92
    不已
    0.92
     Modern
    0.91
     excessive
    0.90
    is
    0.89
     tampoco
    0.89
    Activations Density 0.001%

    No Known Activations