© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 146458
    Prev
    Next
    INDEX
    Explanations

    words in various languages

    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
     Coaching
    0.88
    েন্স
    0.84
     relinquished
    0.77
     আলম
    0.76
    nest
    0.75
     coaching
    0.73
    iglio
    0.73
    }^{*}
    0.72
    भाल
    0.71
    喲
    0.71
    POSITIVE LOGITS
     बे
    0.68
     použ
    0.64
     окно
    0.63
    ipak
    0.62
    кра
    0.61
     রোনাল
    0.61
    岫
    0.60
     fenó
    0.59
    نائ
    0.59
    iries
    0.59
    Activations Density 0.001%

    No Known Activations