© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 8322
    Prev
    Next
    INDEX
    Explanations

    using participles or conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ائص
    0.46
     később
    0.45
     quelquefois
    0.43
    ار
    0.42
    ُر
    0.42
    ើន
    0.41
    ئات
    0.40
    ทำให้
    0.40
     nedenle
    0.40
    }}$;
    0.40
    POSITIVE LOGITS
     using
    0.75
    using
    0.57
     используя
    0.55
     Using
    0.55
     considering
    0.51
     وذلك
    0.50
     usando
    0.49
     assuming
    0.47
     USING
    0.47
     utilizando
    0.46
    Activations Density 0.002%

    No Known Activations