© 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. 11302
    Prev
    Next
    INDEX
    Explanations

    iron deficiency and absorption

    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
    缈
    2.62
    ments
    2.61
     फेड
    2.60
    nales
    2.60
    𝗴
    2.60
    𝗹
    2.50
    别
    2.49
    restassured
    2.47
    𝘂
    2.42
    र्त
    2.42
    POSITIVE LOGITS
    isati
    2.49
    ڈنگ
    2.35
    isna
    2.33
    formula
    2.30
    свя
    2.28
    ."]
    2.26
    ."
    2.24
    "]
    2.19
    ."'
    2.16
    ".
    2.15
    Activations Density 0.019%

    No Known Activations