© 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. 73674
    Prev
    Next
    INDEX
    Explanations

    font size units

    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
    𞤢
    -2.27
    禵
    -1.91
     this
    -1.88
    sukienka
    -1.88
    诓
    -1.84
    kurtka
    -1.82
    艄
    -1.79
     ſame
    -1.71
    鷓
    -1.70
    薆
    -1.68
    POSITIVE LOGITS
    .”
    2.27
    」
    2.23
    }
    2.03
    </code>
    1.89
    ">
    1.84
    ",
    1.80
     Also
    1.77
     また
    1.77
    });
    1.75
    也
    1.70
    Activations Density 0.001%

    No Known Activations