© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129707
    Prev
    Next
    INDEX
    Explanations

    SF followed by abbreviations

    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
    ↵
    -2.55
    蹌
    -1.97
    ла
    -1.91
     theſe
    -1.91
    <i>
    -1.87
     passada
    -1.87
     seleccionamos
    -1.86
     だけ
    -1.83
    或者是
    -1.82
    ギュア
    -1.80
    POSITIVE LOGITS
    (
    2.20
    謦
    2.17
    ("")){
    2.13
    z
    2.05
     não
    2.00
    窳
    2.00
    ])
    1.93
    }$,
    1.91
    ;//
    1.86
    L
    1.85
    Activations Density 0.016%

    No Known Activations