© 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. 48955
    Prev
    Next
    INDEX
    Explanations

    facts about events

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

    foreign or unusual words, crises

    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
    З
    0.46
    Ш
    0.45
    rossover
    0.42
    Ī
    0.41
    푚
    0.40
    <0x06>
    0.40
    ノ
    0.38
    ニ
    0.38
    푎
    0.38
    RELEASE
    0.37
    POSITIVE LOGITS
     famously
    0.66
     unprecedented
    0.52
     literalmente
    0.51
     controvers
    0.50
     необы
    0.49
     عجیب
    0.48
    κή
    0.48
     অদ্ভুত
    0.47
     Amérique
    0.47
     saját
    0.47
    Activations Density 0.067%

    No Known Activations