© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 4020
    Prev
    Next
    INDEX
    Explanations

    scalability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_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
    planatory
    1.89
    боль
    1.83
    ailangan
    1.78
     MIF
    1.78
     DWORD
    1.77
    rectomy
    1.77
    bingen
    1.75
    <unused963>
    1.75
    anniksi
    1.74
     customtkinter
    1.73
    POSITIVE LOGITS
    s
    1.90
     ways
    1.54
    限于
    1.51
     bann
    1.51
     Radiol
    1.43
     time
    1.41
    时间内
    1.40
     contact
    1.39
    ้อมูล
    1.39
     comprend
    1.35
    Activations Density 0.212%

    No Known Activations