© 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. 84486
    Prev
    Next
    INDEX
    Explanations

    word followed by punctuation or code

    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
    诹
    -2.34
     didnt
    -1.95
    ᜀ
    -1.93
     tropicales
    -1.86
    
    -1.85
    麁
    -1.85
    錞
    -1.84
    )–
    -1.81
    CONSIN
    -1.80
     ikke
    -1.73
    POSITIVE LOGITS
    ing
    2.45
    '
    2.17
    谩
    2.09
     télévis
    1.91
    word
    1.90
    2
    1.90
     &
    1.88
    3
    1.87
     În
    1.82
    5
    1.79
    Activations Density 0.008%

    No Known Activations