© 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. 95264
    Prev
    Next
    INDEX
    Explanations

    girls, thou, iconic, invest, decisions, writer

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

    population numbers and metrics

    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
     كتابه
    0.44
     deseo
    0.44
    者的
    0.43
     sostegno
    0.43
     biết
    0.43
    ကြား
    0.43
    <0x0D>
    0.42
    surf
    0.42
    \
    0.42
     bulund
    0.42
    POSITIVE LOGITS
    ถาน
    0.49
    を着
    0.46
     eluted
    0.46
    ᆸ
    0.46
    পিত
    0.46
    Deposito
    0.45
    パターン
    0.45
    empi
    0.44
    িত্য
    0.43
    alary
    0.43
    Activations Density 0.001%

    No Known Activations