© 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. 31-GEMMASCOPE-2-RES-65K
    7. 11921
    Prev
    Next
    INDEX
    Explanations

    frequency or duration

    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
    。
    0.41
    İZ
    0.38
     नतीजे
    0.38
    প্র
    0.38
     Böyle
    0.38
    Rational
    0.37
     Natürlich
    0.37
     soluções
    0.37
    𝗘
    0.37
     prots
    0.37
    POSITIVE LOGITS
    至少
    0.44
     согласно
    0.42
     selama
    0.41
     during
    0.41
     durante
    0.40
     zumindest
    0.39
     během
    0.38
     lessened
    0.38
    少なくとも
    0.38
     tijdens
    0.38
    Activations Density 0.068%

    No Known Activations