© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 5267
    Prev
    Next
    INDEX
    Explanations

    website URLs and 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_65k_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
    īs
    0.68
     (
    0.68
     over
    0.64
    ī
    0.64
     that
    0.63
     with
    0.62
    、
    0.60
     in
    0.59
    （
    0.59
    ...
    0.59
    POSITIVE LOGITS
     Marking
    0.82
     Verh
    0.75
    <unused2013>
    0.75
     riduzione
    0.74
     dalších
    0.74
    ObjectUnderTest
    0.73
    EnglishMarks
    0.73
    ChooseServer
    0.73
    ErrorClazz
    0.73
    <unused963>
    0.73
    Activations Density 0.000%

    No Known Activations