© 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. 174330
    Prev
    Next
    INDEX
    Explanations

    foreign languages or symbols

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

    explaining things to others

    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
    oso
    0.46
    え
    0.45
    Amazon
    0.44
    Nome
    0.44
     a
    0.43
     e
    0.43
    适
    0.42
    El
    0.42
    یں
    0.42
    川
    0.42
    POSITIVE LOGITS
    ség
    0.52
     พระเจ้า
    0.52
     คอม
    0.51
     подели
    0.47
     மாறிய
    0.47
    คอม
    0.47
     처리
    0.47
    StarGo
    0.46
     আনুষ্ঠান
    0.46
     Ouverture
    0.46
    Activations Density 0.001%

    No Known Activations