© 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. 26193
    Prev
    Next
    INDEX
    Explanations

    although / while 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
     only
    -1.31
     caoutchouc
    -1.16
    总之
    -1.11
     demonstrating
    -1.09
    とにかく
    -1.07
     simply
    -1.05
     from
    -1.05
     in
    -1.04
    usions
    -1.01
    という感じ
    -0.99
    POSITIVE LOGITS
     you
    1.63
     I
    1.57
     my
    1.35
     they
    1.25
     we
    1.16
     může
    1.16
    へ向
    1.15
     môže
    1.14
    ónde
    1.13
     mencionados
    1.13
    Activations Density 0.023%

    No Known Activations