© 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. 13-GEMMASCOPE-2-RES-16K
    7. 13931
    Prev
    Next
    INDEX
    Explanations

    Reduced pressure and clinicians

    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_13_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
    𝑚
    2.38
    мии
    2.07
    棿
    2.07
    )}\
    2.05
    𝑎
    2.05
    𝑖
    2.05
    theless
    2.02
    ERIAL
    2.01
    ῥ
    2.00
    渫
    1.96
    POSITIVE LOGITS
    য়ের
    1.73
    heu
    1.71
    graphics
    1.68
    ached
    1.65
    য়ের
    1.63
    traf
    1.63
    agad
    1.63
    uciones
    1.56
    iciente
    1.56
    hend
    1.54
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.