© 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. 2576
    Prev
    Next
    INDEX
    Explanations

    specialized terms

    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
    6
    0.63
    8
    0.63
    7
    0.61
    Type
    0.59
    ل
    0.57
    9
    0.57
    徎
    0.57
    نا
    0.56
    ρίας
    0.56
    ной
    0.55
    POSITIVE LOGITS
     the
    0.93
     cinq
    0.74
     escolas
    0.73
     deux
    0.73
     quatro
    0.71
     two
    0.69
     pequeno
    0.69
     zwei
    0.68
     racconto
    0.68
     arbres
    0.68
    Activations Density 1.227%

    No Known Activations