© 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
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10908
    Prev
    Next
    INDEX
    Explanations

    code class definitions

    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
    ্ম্ম
    2.40
    ۰۰
    2.27
    μφ
    2.18
    <bos>
    2.09
    𝚕
    2.05
     تردد
    1.98
    jení
    1.98
    jima
    1.96
    jska
    1.95
    scrollbar
    1.94
    POSITIVE LOGITS
    s
    2.58
    n
    2.54
    ن
    2.40
    いる
    2.31
     ";
    2.29
    non
    2.27
     HAPP
    2.23
    nT
    2.21
    𝐢
    2.16
    ㄻ
    2.13
    Activations Density 0.014%

    No Known Activations