© 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-16K
    7. 14146
    Prev
    Next
    INDEX
    Explanations

    small frequent tuple

    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
     when
    0.33
     during
    0.31
     before
    0.31
     with
    0.29
     but
    0.26
     while
    0.26
    when
    0.26
     -
    0.25
     after
    0.25
     quando
    0.25
    POSITIVE LOGITS
     работают
    0.21
     είναι
    0.19
     жизнь
    0.19
     живут
    0.18
    قیع
    0.18
    ология
    0.18
     पेशे
    0.18
     డబ్బు
    0.17
    פו
    0.17
    Điều
    0.17
    Activations Density 0.001%

    No Known Activations