© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 9167
    Prev
    Next
    INDEX
    Explanations

    title word

    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
     sobres
    1.09
     stadium
    1.01
    潸
    1.01
     appreciable
    0.99
    ˬ
    0.97
     Jetty
    0.92
     jetty
    0.90
     varsity
    0.89
    쿱
    0.89
     klad
    0.87
    POSITIVE LOGITS
    holder
    1.24
     deeds
    1.14
    holders
    1.13
    page
    1.09
     sponsor
    1.06
    deeds
    1.05
     Deeds
    0.98
     IX
    0.97
    pagina
    0.94
     Insurance
    0.94
    Activations Density 0.031%

    No Known Activations