© 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. 10222
    Prev
    Next
    INDEX
    Explanations

    err on the side of caution

    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
    Negative Logits
     здание
    2.35
    𝚘
    2.29
    ⁩
    2.17
    мого
    2.16
    𝚛
    2.10
    цкий
    2.09
    眦
    2.09
    徇
    2.03
    inito
    2.02
    ক
    1.95
    POSITIVE LOGITS
    <bos>
    2.99
    ferred
    2.46
    atche
    2.44
    ாக்கு
    2.42
    úncia
    2.41
    като
    2.40
     एनटी
    2.27
    岖
    2.24
    inherit
    2.19
    cription
    2.17
    Activations Density 0.040%

    No Known Activations