© 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. 7639
    Prev
    Next
    INDEX
    Explanations

    descriptive words and "home"

    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
    ཌ
    -1.77
    
    -1.73
                        
    -1.58
    擼
    -1.52
    interested
    -1.48
    をあ
    -1.45
    雠
    -1.45
     ſever
    -1.43
    thers
    -1.43
    稣
    -1.40
    POSITIVE LOGITS
     and
    1.83
     because
    1.82
     of
    1.80
     or
    1.80
     but
    1.60
     now
    1.56
     when
    1.52
     for
    1.52
     even
    1.49
    ↵
    1.43
    Activations Density 0.005%

    No Known Activations