© 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. 84976
    Prev
    Next
    INDEX
    Explanations

    numbers followed by a letter

    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
     came
    -2.81
     went
    -2.66
     decided
    -2.59
     gave
    -2.59
    
    -2.58
    岀
    -2.53
    啸
    -2.52
     makes
    -2.50
     from
    -2.48
     gets
    -2.48
    POSITIVE LOGITS
    4
    3.50
    6
    3.05
    You
    2.88
    厹
    2.83
    “,
    2.83
    selbe
    2.83
    3
    2.78
    ↵
    2.64
     
    2.64
    2
    2.63
    Activations Density 0.062%

    No Known Activations