© 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-16K
    7. 7565
    Prev
    Next
    INDEX
    Explanations

    as possible

    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_16k_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
     Plenty
    0.70
     잘못
    0.65
    ಸ್ಯ
    0.65
    蛙
    0.64
     に関
    0.64
     misalkan
    0.62
    ന്തര
    0.62
     plenty
    0.62
    就需要
    0.61
    宮
    0.61
    POSITIVE LOGITS
     possible
    1.93
     possível
    1.78
     wherever
    1.75
    possible
    1.75
     practicable
    1.70
     posible
    1.70
     possibile
    1.69
     Possible
    1.66
     whenever
    1.58
    Possible
    1.58
    Activations Density 0.113%

    No Known Activations