© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 84248
    Prev
    Next
    INDEX
    Explanations

    quantities and fractions

    np_acts-logits-general · gemini-2.5-flash-lite

    percentages and approximations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bal
    0.43
     pointless
    0.41
    `);
    0.41
     breat
    0.40
     erros
    0.40
     trivial
    0.40
     meaningless
    0.39
    );
    0.39
    `;
    0.39
     grave
    0.39
    POSITIVE LOGITS
    гистра
    0.46
     contiennent
    0.44
    Между
    0.44
    大多數
    0.44
     የተለያዩ
    0.42
    omètre
    0.41
     বেশিরভাগ
    0.41
     오전
    0.41
     තම
    0.41
     করেছি
    0.40
    Activations Density 0.011%

    No Known Activations