© 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. 66887
    Prev
    Next
    INDEX
    Explanations

    l' followed by e or a sound

    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
    三個
    -2.16
    𐐪
    -2.02
    itarianism
    -2.00
    quirer
    -1.98
    鉭
    -1.95
     divertida
    -1.95
    ⡪
    -1.87
    蛻
    -1.86
    Detta
    -1.84
    ズニー
    -1.84
    POSITIVE LOGITS
    轳
    2.13
    蒾
    1.95
    ⟝
    1.95
    鼋
    1.91
    }
    1.90
    “
    1.85
    ategori
    1.84
    '
    1.82
     Lös
    1.81
    事的
    1.80
    Activations Density 0.002%

    No Known Activations