© 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. 3846
    Prev
    Next
    INDEX
    Explanations

    song intros

    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
    า
    2.96
     nascetur
    2.96
    ेक्षित
    2.79
    ാ
    2.68
    ിയും
    2.49
    ៊ី
    2.44
    ेड
    2.43
    ieri
    2.41
    WERS
    2.39
    artney
    2.36
    POSITIVE LOGITS
    <bos>
    3.34
    дал
    2.47
    ven
    2.27
    velle
    2.25
    haan
    2.23
    ब्रेरी
    2.22
    vem
    2.20
    plin
    2.19
    orthy
    2.18
    クセル
    2.17
    Activations Density 0.013%

    No Known Activations