© 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-262K
    7. 47549
    Prev
    Next
    INDEX
    Explanations

    biographical details

    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_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
    t
    0.70
    tım
    0.54
    tiene
    0.52
    tor
    0.52
    tur
    0.52
    haba
    0.51
    trem
    0.51
    sadquotes
    0.51
    sites
    0.50
    tdd
    0.50
    POSITIVE LOGITS
     μεγαλύτε
    0.48
     Replace
    0.46
     পূর্ণ
    0.46
    0
    0.46
     tät
    0.44
     replace
    0.43
    変更
    0.43
     কিন্তু
    0.42
     artwork
    0.42
     અન્ય
    0.42
    Activations Density 0.003%

    No Known Activations