© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99580
    Prev
    Next
    INDEX
    Explanations

    even adding or including

    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
     also
    -2.25
    also
    -1.88
     également
    -1.86
     and
    -1.86
    \
    -1.76
     також
    -1.74
    とにかく
    -1.71
     również
    -1.70
     גם
    -1.66
     ebenfalls
    -1.60
    POSITIVE LOGITS
     their
    1.70
     esfuer
    1.67
     resultaat
    1.66
    𖤣
    1.62
     podría
    1.56
     today
    1.51
     může
    1.48
    titanium
    1.48
     those
    1.46
     changes
    1.46
    Activations Density 0.047%

    No Known Activations