© 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. 84299
    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_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
     that
    -2.50
     would
    -2.42
     need
    -2.08
     will
    -2.08
     must
    -1.96
     when
    -1.93
    {
    -1.85
     deberán
    -1.74
    5
    -1.73
    ꔛ
    -1.72
    POSITIVE LOGITS
     fermer
    2.13
    躥
    2.13
     blanda
    2.11
     categorie
    2.03
     nahil
    2.00
     maten
    1.98
     maniere
    1.96
     vasi
    1.95
     gratuite
    1.94
    
    1.92
    Activations Density 0.255%

    No Known Activations