© 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. 21645
    Prev
    Next
    INDEX
    Explanations

    foreign languages and quantifiers

    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
    \
    0.46
    {
    0.45
    refs
    0.44
    ref
    0.44
    title
    0.44
    https
    0.43
    radio
    0.43
    reminder
    0.42
     üst
    0.41
    ("<
    0.41
    POSITIVE LOGITS
     после
    0.47
     जब
    0.46
     después
    0.46
     পিক
    0.45
     సాధారణ
    0.44
     Após
    0.44
     Normalmente
    0.44
     flamenco
    0.43
     quando
    0.43
     څرنګوالی
    0.43
    Activations Density 0.002%

    No Known Activations