© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 116975
    Prev
    Next
    INDEX
    Explanations

    Jewish people

    np_acts-logits-general · gemini-2.5-flash-lite

    punctuation and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odzi
    0.54
    osta
    0.47
    зем
    0.47
    etiti
    0.47
    д
    0.46
    etna
    0.46
    кти
    0.46
    ate
    0.45
    ochemistry
    0.45
     ей
    0.45
    POSITIVE LOGITS
    ەس
    0.47
    跆
    0.46
    হু
    0.44
     dansk
    0.44
     sujet
    0.43
    হাম
    0.43
    ირო
    0.42
     showbiz
    0.41
    ח
    0.41
     baseball
    0.40
    Activations Density 0.000%

    No Known Activations