© 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. 10118
    Prev
    Next
    INDEX
    Explanations

    approximate quantities

    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
    ்டர்
    3.40
    cracker
    3.09
    сным
    2.93
    ي
    2.82
    izó
    2.74
    ্কর
    2.73
    aży
    2.67
    тэ
    2.61
    uais
    2.60
    ెర
    2.60
    POSITIVE LOGITS
    <bos>
    2.98
    ️
    2.92
    nel
    2.53
    na
    2.46
     o
    2.38
     DISCLAIMED
    2.33
    adays
    2.33
    ه‌
    2.24
    ”…
    2.18
    no
    2.17
    Activations Density 0.021%

    No Known Activations