© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 147900
    Prev
    Next
    INDEX
    Explanations

    Python code and accessibility insights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
    Animal
    0.75
    Street
    0.69
    䧣
    0.69
    Carrito
    0.69
     Tumor
    0.67
    Tipo
    0.67
    Ult
    0.66
     बंदूक
    0.65
    thead
    0.65
    üd
    0.63
    POSITIVE LOGITS
     meanings
    0.83
    ﻵ
    0.82
     몰
    0.69
     responses
    0.69
    玑
    0.68
    故
    0.67
     کمتر
    0.66
    聋
    0.66
    possibleTypes
    0.66
    更多的
    0.66
    Activations Density 0.002%

    No Known Activations