© 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. 22-GEMMASCOPE-RES-131K
    7. 39155
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by verb

    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
     Egyp
    -1.05
     Chinois
    -1.04
     PED
    -0.98
    Apa
    -0.93
     Majefty
    -0.92
     plafond
    -0.89
     papillon
    -0.88
     redirection
    -0.87
     organisme
    -0.86
     دقیق
    -0.86
    POSITIVE LOGITS
     richied
    1.07
     which
    1.03
     fábricas
    1.00
     For
    0.97
     any
    0.96
     terlibat
    0.96
     their
    0.95
     whose
    0.94
     who
    0.92
     involved
    0.92
    Activations Density 0.082%

    No Known Activations