© 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. 22-GEMMASCOPE-2-RES-16K
    7. 5657
    Prev
    Next
    INDEX
    Explanations

    suggestions and subtle hints

    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_22_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
    ''(
    0.69
    itical
    0.66
    <unused381>
    0.64
    ău
    0.64
    辖
    0.64
    acuda
    0.63
    ős
    0.63
    <unused2092>
    0.62
    łych
    0.62
     predecessor
    0.62
    POSITIVE LOGITS
     letting
    0.74
     Let
    0.74
     கேட்டு
    0.72
    وای
    0.70
     Lets
    0.70
     ইচ্ছ
    0.68
     Comun
    0.68
     let
    0.67
    Let
    0.66
    朝着
    0.66
    Activations Density 0.091%

    No Known Activations