© 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. 31323
    Prev
    Next
    INDEX
    Explanations

    naming origins and context

    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
    ż
    0.44
    this
    0.43
    iciones
    0.41
     This
    0.40
    visitors
    0.39
     Это
    0.39
    э
    0.39
    рав
    0.38
     нати
    0.38
     это
    0.38
    POSITIVE LOGITS
     شخصیت
    0.52
    爌
    0.47
     Patreon
    0.46
     agonist
    0.46
    mêmes
    0.44
    ពួក
    0.43
     گلوکار
    0.43
    شده
    0.43
     mesmos
    0.43
     isomeric
    0.42
    Activations Density 0.003%

    No Known Activations