© 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. 22-GEMMASCOPE-RES-131K
    7. 12443
    Prev
    Next
    INDEX
    Explanations

    also / additionally

    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
     this
    -1.19
    grees
    -0.94
     только
    -0.90
    ين
    -0.88
     that
    -0.88
     which
    -0.86
     было
    -0.85
     heuer
    -0.85
     each
    -0.85
     according
    -0.84
    POSITIVE LOGITS
     also
    2.81
     також
    1.77
     também
    1.77
     también
    1.68
     også
    1.67
     myös
    1.66
     также
    1.65
    Also
    1.53
     també
    1.48
     juga
    1.43
    Activations Density 0.135%

    No Known Activations