© 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. 43737
    Prev
    Next
    INDEX
    Explanations

    AS-IS

    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
    ];
    -1.59
     I
    -1.55
     blisko
    -1.45
    </h4>
    -1.44
     Zerst
    -1.39
    };
    -1.37
     then
    -1.35
    mathrm
    -1.35
     rígida
    -1.35
    aarrggbb
    -1.34
    POSITIVE LOGITS
    </i>
    2.23
     negó
    1.70
     semakin
    1.66
     advirtió
    1.63
    🕗
    1.63
    توضیحات
    1.59
     не
    1.55
    стями
    1.48
    втра
    1.45
    Zubereitung
    1.42
    Activations Density 0.008%

    No Known Activations