© 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. 40-GEMMASCOPE-2-RES-262K
    7. 169019
    Prev
    Next
    INDEX
    Explanations

    foreign words and symbols

    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_40_width_262k_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
    ότερα
    0.45
     Bhi
    0.41
    ๒
    0.41
    授業
    0.40
    abilă
    0.40
    剥
    0.40
    १८४
    0.39
    乘以
    0.39
    连
    0.39
     ສຳ
    0.39
    POSITIVE LOGITS
     niche
    0.47
     mev
    0.41
     wants
    0.40
     evol
    0.39
     specializing
    0.39
     ending
    0.39
     psycho
    0.39
     financial
    0.39
     occult
    0.39
     evolutionary
    0.38
    Activations Density 0.000%

    No Known Activations