© 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. 72309
    Prev
    Next
    INDEX
    Explanations

    if/when/before clauses

    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
    rored
    -1.24
     verkligen
    -1.16
     därför
    -1.13
    ALITY
    -1.13
    他們的
    -1.12
     individ
    -1.11
    いって
    -1.09
    GGLE
    -1.08
     dessutom
    -1.04
     vider
    -1.03
    POSITIVE LOGITS
     if
    2.89
     unless
    1.84
     whether
    1.65
     before
    1.40
     если
    1.39
     when
    1.39
     until
    1.34
     either
    1.33
     якщо
    1.31
     should
    1.29
    Activations Density 0.003%

    No Known Activations