© 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. 10897
    Prev
    Next
    INDEX
    Explanations

    以...为

    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
    악
    2.52
    도가
    2.41
    도를
    2.40
    stackpath
    2.36
    도의
    2.35
    롬
    2.34
    𝓾
    2.32
    ྫ
    2.32
    hes
    2.30
    hoy
    2.30
    POSITIVE LOGITS
    ToOne
    2.62
    autan
    2.58
    en
    2.50
    色列
    2.45
     mt
    2.40
    یثیت
    2.40
    rons
    2.39
    enb
    2.34
     Grave
    2.33
     cri
    2.32
    Activations Density 0.000%

    No Known Activations