© 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-65K
    7. 7088
    Prev
    Next
    INDEX
    Explanations

    do you

    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
    lands
    1.14
     there
    1.13
    there
    1.11
    ne
    1.01
    um
    1.00
    rete
    0.98
    ness
    0.98
    y
    0.96
    cote
    0.95
    power
    0.95
    POSITIVE LOGITS
    ுகிறது
    1.13
    pped
    1.05
    ppers
    1.00
    𝐒
    0.93
     celebrities
    0.90
    不同
    0.87
     pathologists
    0.87
    的是
    0.86
    ED
    0.86
     conglomerates
    0.85
    Activations Density 0.047%

    No Known Activations