© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14658
    Prev
    Next
    INDEX
    Explanations

    reflexive pronouns describing self-perception

    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
     they
    -1.77
     all
    -1.72
     their
    -1.70
     when
    -1.59
     it
    -1.56
     that
    -1.55
     bahwa
    -1.55
     Then
    -1.54
     What
    -1.54
     before
    -1.54
    POSITIVE LOGITS
    婓
    1.49
    泂
    1.44
    begin
    1.44
     zout
    1.43
     увеличить
    1.41
     itr
    1.40
     mots
    1.38
    currently
    1.38
     exac
    1.37
    uccess
    1.36
    Activations Density 0.009%

    No Known Activations