© 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. 888
    Prev
    Next
    INDEX
    Explanations

    on-boarding; onion skinning

    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
    Error
    1.13
    Pada
    1.12
     Pada
    1.12
    volle
    1.11
     pada
    1.08
    bowl
    1.03
    ে
    1.02
     മൊ
    1.02
    dle
    1.01
    ми
    1.01
    POSITIVE LOGITS
     behalf
    2.39
    slaught
    1.91
     horseback
    1.52
     occasion
    1.51
    estep
    1.49
    ৈতিক
    1.44
     top
    1.43
    eway
    1.42
    GOING
    1.40
     keresztül
    1.39
    Activations Density 0.170%

    No Known Activations