© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2808
    Prev
    Next
    INDEX
    Explanations

    the digit 5

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    5.14
    ВД
    3.06
    ী
    2.95
    :'
    2.69
    AWSJavaScriptSDK
    2.65
     cuantos
    2.61
    ogast
    2.59
    nt
    2.57
    компа
    2.51
    pentine
    2.49
    POSITIVE LOGITS
    ायती
    2.97
    ﺮ
    2.76
    الي
    2.76
    ennzeichnet
    2.64
    ⓗ
    2.64
    hevik
    2.54
    ené
    2.53
    ้า
    2.52
    çou
    2.52
    𝐮
    2.51
    Activations Density 0.484%

    No Known Activations