© 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. 69936
    Prev
    Next
    INDEX
    Explanations

    segment or duration

    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
    enablog
    -2.69
    盌
    -2.61
    Ꮣ
    -2.44
    Ꮉ
    -2.44
    ſſel
    -2.42
     استخدام
    -2.41
    鐽
    -2.41
    ⢊
    -2.36
    ⁉
    -2.36
    隨著
    -2.31
    POSITIVE LOGITS
    ).
    3.33
    ),
    3.16
    ↵
    3.09
    ",
    3.00
    ))
    2.92
    ],
    2.86
    ’
    2.75
     sabotage
    2.70
     \\
    2.69
    </em>
    2.67
    Activations Density 0.005%

    No Known Activations