© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99322
    Prev
    Next
    INDEX
    Explanations

    suppose or if followed by a subject

    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
     якщо
    -1.48
    glicher
    -1.45
     если
    -1.41
     jeśli
    -1.35
     and
    -1.34
     pokud
    -1.30
    kedés
    -1.23
     אם
    -1.19
    tidos
    -1.15
    crimination
    -1.13
    POSITIVE LOGITS
     we
    2.56
     instead
    2.53
     you
    1.89
     invece
    1.81
    Instead
    1.73
     вместо
    1.70
    instead
    1.67
     someone
    1.55
     zamiast
    1.55
     Instead
    1.54
    Activations Density 0.077%

    No Known Activations