© 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. 211322
    Prev
    Next
    INDEX
    Explanations

    off, against, less

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

    foreign names and contexts

    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
    जीत
    0.52
    formulario
    0.48
    ayad
    0.46
     reembolso
    0.45
    ț
    0.45
    чение
    0.44
     آمر
    0.43
    ayutt
    0.43
    carrito
    0.42
    tattoo
    0.42
    POSITIVE LOGITS
    之内
    0.51
    上に
    0.49
    内的
    0.45
    研究生
    0.45
     nhưng
    0.45
    下的
    0.45
     αλλά
    0.45
    下
    0.45
    外
    0.44
    蛮
    0.44
    Activations Density 0.001%

    No Known Activations