© 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. 84343
    Prev
    Next
    INDEX
    Explanations

    is followed by modal verbs

    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
     ditangkap
    -1.23
     eivät
    -1.16
    Бил
    -1.12
    ついに
    -1.10
    щі
    -1.09
    枇
    -1.09
    ‫‪
    -1.04
    Ах
    -1.03
     melap
    -1.01
     колба
    -1.01
    POSITIVE LOGITS
     will
    1.76
     is
    1.61
     should
    1.36
     can
    1.32
     would
    1.30
     could
    1.13
     must
    1.06
     tzw
    1.05
     might
    1.03
    ac
    0.97
    Activations Density 0.067%

    No Known Activations