© 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. 14217
    Prev
    Next
    INDEX
    Explanations

    root cause

    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
    slideClass
    2.49
    pulsewidth
    2.45
    ষেধ
    2.39
     proguardFiles
    2.38
     thiệu
    2.37
     zmdi
    2.37
     退
    2.35
     elevationMap
    2.33
    Ｍ
    2.33
     thisComponent
    2.33
    POSITIVE LOGITS
    u
    2.86
    y
    2.84
     التربيع
    2.34
    estown
    2.22
    ו
    2.19
    arjo
    2.17
    haar
    2.14
    ar
    2.13
    enance
    2.10
    ين
    2.04
    Activations Density 0.046%

    No Known Activations