© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 110893
    Prev
    Next
    INDEX
    Explanations

    link, text, handle, blanket, colors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trabajadores
    0.47
    ুখ
    0.46
     மாசுபடுத்த
    0.46
    ногие
    0.45
     cuerpos
    0.45
     motores
    0.45
    ன்ஸ்
    0.45
    鲽
    0.45
    是一种
    0.44
     confine
    0.44
    POSITIVE LOGITS
    )}-
    0.45
    dri
    0.43
    ซื้อ
    0.41
     архів
    0.41
    archiw
    0.40
    閱
    0.40
     
    0.40
     Wyn
    0.40
    ≈
    0.40
    DVD
    0.39
    Activations Density 0.002%

    No Known Activations