© 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. 3537
    Prev
    Next
    INDEX
    Explanations

    necessity or demand

    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
    ಸ್ಸ
    3.20
    מיד
    2.97
    स
    2.86
    ೋಜನ
    2.81
    NSE
    2.72
    <bos>
    2.71
    тріш
    2.68
    Prz
    2.67
    сці
    2.65
    DEFGHI
    2.62
    POSITIVE LOGITS
    ming
    3.30
    ことができる
    3.26
    mler
    3.05
    mu
    3.01
    tat
    2.83
    nya
    2.82
    mi
    2.81
    了
    2.77
    🏻
    2.72
    mit
    2.71
    Activations Density 0.111%

    No Known Activations