© 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. 7509
    Prev
    Next
    INDEX
    Explanations

    information and instructions

    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
    قابل
    2.14
     thế
    2.11
    رض
    2.08
     stam
    2.06
    ηγ
    2.04
    膘
    2.03
    epo
    2.03
    рай
    2.02
    stw
    2.00
    אס
    1.99
    POSITIVE LOGITS
    <b>
    1.41
    <strong>
    1.20
    支出
    0.98
    HttpSession
    0.98
     eigenstates
    0.97
     Blueprint
    0.97
     Physicians
    0.96
     Drawer
    0.93
     Instrum
    0.92
     Sacrament
    0.92
    Activations Density 0.001%

    No Known Activations