© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 15211
    Prev
    Next
    INDEX
    Explanations

    text characters and punctuation removal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
    일상
    0.97
    විත
    0.95
     dijadikan
    0.95
     mengenal
    0.95
    )}`;
    0.92
    េទ
    0.91
    自己的
    0.91
     afternoons
    0.91
     exs
    0.90
     như
    0.89
    POSITIVE LOGITS
    En
    0.75
    edin
    0.72
    焗
    0.72
    ras
    0.70
     Okay
    0.66
    en
    0.66
    '
    0.66
    ron
    0.66
    Neil
    0.66
     En
    0.66
    Activations Density 0.001%

    No Known Activations