© 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. 1348
    Prev
    Next
    INDEX
    Explanations

    obsolescence

    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
    <unused2197>
    1.12
    
    1.05
     وذلك
    1.05
    <unused2221>
    1.01
    <unused2199>
    1.00
    <unused2169>
    0.97
     살펴보도록
    0.94
    することができます
    0.94
     LongNumber
    0.93
     bulunmaktadır
    0.92
    POSITIVE LOGITS
    /
    1.49
     etc
    1.42
    (?)
    1.10
     despite
    1.06
    +
    1.06
     AFTER
    1.05
     after
    1.04
     (?)
    1.03
     without
    1.01
     if
    1.01
    Activations Density 1.126%

    No Known Activations