© 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. 9014
    Prev
    Next
    INDEX
    Explanations

    you need help or want more

    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
    ?:
    1.05
    HELLO
    1.01
     Hello
    1.01
    ?(
    0.98
    (?:
    0.98
    (...
    0.97
     Anybody
    0.96
    (...)
    0.94
     miglia
    0.94
    ](
    0.93
    POSITIVE LOGITS
     agreed
    1.31
     agrees
    1.27
     agreeing
    1.25
     agree
    1.23
     concurred
    1.17
     reminds
    1.12
     exactly
    1.07
     اتفق
    1.00
     reminded
    0.98
     underlines
    0.97
    Activations Density 0.200%

    No Known Activations