© 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. 13522
    Prev
    Next
    INDEX
    Explanations

    Shift key combinations

    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
    𒅖
    2.14
    𒈪
    2.13
    FURNIZOR
    2.13
    𒀫
    2.12
    𒅴
    2.12
    𒅅
    2.11
    𒄖
    2.10
    𒌅
    2.10
     प्रीकम
    2.09
    𒌈
    2.08
    POSITIVE LOGITS
     department
    1.22
     intended
    1.12
     additionally
    1.11
     also
    1.10
     which
    1.05
     will
    1.05
     products
    1.04
     associate
    1.03
     departments
    1.01
     associated
    1.01
    Activations Density 0.217%

    No Known Activations