© 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. 136304
    Prev
    Next
    INDEX
    Explanations

    periodic reports

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

    Industry, format, resistance, choir, Belarusian

    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
    coin
    0.51
    (-(
    0.50
    akespeare
    0.50
     автома
    0.50
    гре
    0.49
    ătoare
    0.48
     монет
    0.47
    il
    0.47
    <tbody>
    0.46
    isim
    0.46
    POSITIVE LOGITS
    دارة
    0.47
    مرار
    0.46
    成年
    0.44
    出国
    0.43
    شهاد
    0.42
    伦敦
    0.42
     vanilla
    0.41
    ভারতে
    0.41
     Weihnacht
    0.41
    享受
    0.41
    Activations Density 0.001%

    No Known Activations