© 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. 10-GEMMASCOPE-RES-131K
    7. 85440
    Prev
    Next
    INDEX
    Explanations

    separators in 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_10/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
     вже
    -1.84
    Already
    -1.80
    already
    -1.77
     Уже
    -1.63
     adecuados
    -1.52
     Already
    -1.48
     Zijn
    -1.47
     všetky
    -1.46
     rajut
    -1.45
     kwamen
    -1.42
    POSITIVE LOGITS
     for
    1.70
     but
    1.59
     selfish
    1.30
     because
    1.26
    le
    1.26
     can
    1.25
     tons
    1.22
    越大
    1.21
    licante
    1.21
     in
    1.20
    Activations Density 0.025%

    No Known Activations