© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 28863
    Prev
    Next
    INDEX
    Explanations

    punctuation and Chinese words

    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_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
     to
    1.30
    ,
    1.28
     paradise
    1.27
     می
    1.27
     blatant
    1.25
     were
    1.20
     lucu
    1.20
     lair
    1.18
     harem
    1.17
     bastion
    1.16
    POSITIVE LOGITS
    。
    1.84
    '
    1.75
    न
    1.52
    ।
    1.51
    、
    1.37
    (
    1.35
    н
    1.16
    ों
    1.13
    ه
    1.13
    ă
    1.13
    Activations Density 0.003%

    No Known Activations