© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 73969
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by a 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
    corrhi
    -1.59
     だっ
    -1.59
     extraordin
    -1.56
     великолеп
    -1.53
     diretor
    -1.50
     あります
    -1.49
     anex
    -1.48
     incess
    -1.44
     роско
    -1.44
     namorados
    -1.41
    POSITIVE LOGITS
     also
    3.41
     then
    2.47
     however
    1.92
    そして
    1.85
     is
    1.68
     therefore
    1.67
     thus
    1.63
     was
    1.63
    irs
    1.61
     certainly
    1.59
    Activations Density 0.167%

    No Known Activations