© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 59606
    Prev
    Next
    INDEX
    Explanations

    Caroline Holden

    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
     زاويه
    0.40
    やり
    0.37
     flujo
    0.37
     commerciale
    0.35
    ጐ
    0.35
    ገኛ
    0.35
    ̻
    0.35
    वाली
    0.34
    Fe
    0.34
     tira
    0.34
    POSITIVE LOGITS
    িনায়ক
    0.44
    masked
    0.41
    })
    0.38
    bonus
    0.38
    lucene
    0.38
     masked
    0.38
     af
    0.37
    到现在
    0.37
     apel
    0.36
    ninger
    0.36
    Activations Density 0.001%

    No Known Activations