© 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. 16-GEMMASCOPE-2-RES-65K
    7. 3366
    Prev
    Next
    INDEX
    Explanations

    first word of phrase

    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_16_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
    ม
    0.56
    াহ
    0.50
    ar
    0.47
    yn
    0.44
    ad
    0.44
    Azer
    0.44
    </em>
    0.44
    ল
    0.43
    й
    0.42
    ap
    0.42
    POSITIVE LOGITS
     α
    0.48
     discredited
    0.47
    ‘
    0.47
     των
    0.46
     thousand
    0.46
    }}$,
    0.45
    ۰
    0.45
    дцать
    0.44
     بنابراین
    0.44
     χρήση
    0.44
    Activations Density 0.000%

    No Known Activations