© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 3761
    Prev
    Next
    INDEX
    Explanations

    `(__name` and `exit` in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     the
    1.27
     over
    1.20
     you
    1.16
    ,
    1.16
     online
    1.14
     and
    1.12
     a
    1.09
     your
    1.08
     to
    1.06
     all
    1.05
    POSITIVE LOGITS
    CollectedField
    1.35
    executionContext
    1.33
    ującego
    1.25
    перыі
    1.24
    UCLEAR
    1.24
    Namespace
    1.23
    <unused16>
    1.23
    >\<^
    1.21
    yní
    1.20
    aksanakan
    1.20
    Activations Density 0.034%

    No Known Activations