© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7103
    Prev
    Next
    INDEX
    Explanations

    execution, help, genetic, borrow

    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_22_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
     갑
    0.92
     outbursts
    0.91
    やお
    0.89
     raging
    0.85
     잠깐
    0.84
    သား
    0.83
    են
    0.83
     benefited
    0.82
     sparked
    0.82
    饑
    0.82
    POSITIVE LOGITS
     edeb
    1.17
     pravidel
    1.16
     kond
    1.09
     रखरखाव
    1.07
     konstru
    1.06
    onter
    1.03
     muss
    1.02
     possibilité
    1.02
     sửa
    1.00
     thuyết
    0.99
    Activations Density 0.000%

    No Known Activations