© 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. 26380
    Prev
    Next
    INDEX
    Explanations

    if statements

    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
     También
    -1.35
     también
    -1.23
     även
    -1.20
    gså
    -1.11
    tranh
    -1.10
     erfaring
    -1.08
     comerciantes
    -1.08
     första
    -1.08
    même
    -1.06
     même
    -1.05
    POSITIVE LOGITS
     if
    2.09
    if
    1.35
     when
    1.27
    If
    1.24
     (
    1.18
     если
    1.16
     unless
    1.15
    IfNeeded
    1.15
     caffè
    1.10
     on
    1.08
    Activations Density 0.004%

    No Known Activations