© 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. 10835
    Prev
    Next
    INDEX
    Explanations

    email regex patterns

    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
    ued
    2.20
    uei
    2.08
    h
    2.05
    rantes
    2.05
    XXXX
    1.98
    ्ला
    1.96
    สาน
    1.96
    struck
    1.95
     and
    1.95
    d
    1.95
    POSITIVE LOGITS
    ocsát
    2.25
    犸
    2.21
    يرة
    2.08
    يره
    2.05
    يبة
    2.03
    ängen
    1.89
    ⃝
    1.87
    izam
    1.85
    सर्गिक
    1.85
    फारिश
    1.84
    Activations Density 0.018%

    No Known Activations