© 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. 58499
    Prev
    Next
    INDEX
    Explanations

    ) followed by word

    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
        
    -1.74
    ,"
    -1.55
    >
    -1.47
     

    -1.45
    },
    -1.43
    

    -1.40
     who
    -1.40
    ではない
    -1.39
    ле
    -1.38
    in
    -1.38
    POSITIVE LOGITS
    ῞
    1.91
     them
    1.66
     内衣
    1.65
     薬局
    1.64
    ってる
    1.62
    槩
    1.62
    écoute
    1.59
     entanto
    1.55
    But
    1.55
    ția
    1.55
    Activations Density 0.071%

    No Known Activations