© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 42558
    Prev
    Next
    INDEX
    Explanations

    labor of love

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

    align with or want

    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
     الفاظ
    0.51
    etzten
    0.49
    ointments
    0.46
     مجبور
    0.45
     ಹಿಂದೆ
    0.45
    ’
    0.44
    гать
    0.44
    ថ
    0.44
     இடை
    0.44
     ज़ि
    0.43
    POSITIVE LOGITS
    </h2>
    0.47
    0
    0.47
     Chain
    0.46
    ↵↵
    0.45
     Cardiovascular
    0.44
    <h2>
    0.43
     periodic
    0.42
    谢谢
    0.42
    ύν
    0.41
    </code>
    0.41
    Activations Density 0.000%

    No Known Activations