© 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. 31-GEMMASCOPE-2-RES-65K
    7. 55327
    Prev
    Next
    INDEX
    Explanations

    numbers and different concepts

    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/layer_31_width_65k_l0_medium
    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
     m
    0.58
     bra
    0.54
     D
    0.49
    ;
    0.45
     an
    0.45
     using
    0.44
     for
    0.43
     a
    0.43
     mosa
    0.42
     robert
    0.42
    POSITIVE LOGITS
    दो
    0.48
    सत्ता
    0.47
    ikte
    0.46
    ambahkan
    0.45
     επίσης
    0.43
    ষ্ঠান
    0.43
     करण्याची
    0.43
    то
    0.42
    ሎች
    0.41
    мимо
    0.41
    Activations Density 0.003%

    No Known Activations