© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2314
    Prev
    Next
    INDEX
    Explanations

    other languages and numerals

    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_16k_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
     무
    0.37
    0.36
    час
    0.35
    Ê
    0.34
     [
    0.33
     highly
    0.32
     stammt
    0.31
     تُ
    0.31
     $\
    0.30
     nucleus
    0.30
    POSITIVE LOGITS
     आल्सो
    0.42
     другие
    0.40
     অথবা
    0.39
     അദ്ദേ
    0.38
    所以我
    0.38
    其他人
    0.38
     மற்றொரு
    0.38
     विशेषताएं
    0.38
     અન્ય
    0.37
     drugih
    0.37
    Activations Density 0.675%

    No Known Activations