© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2444
    Prev
    Next
    INDEX
    Explanations

    communication and states

    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
    /
    1.64
    -/
    1.37
     รวมถึง
    1.14
     (\"
    1.13
     mainly
    1.13
    /"
    1.12
     chiefly
    1.12
     (=
    1.11
     /
    1.09
     mostly
    1.08
    POSITIVE LOGITS
     ஒரு
    0.78
    Một
    0.73
     सम्मान
    0.73
    validator
    0.71
    ஒரு
    0.71
     uncertainty
    0.69
    uncertain
    0.69
    Мы
    0.68
     પ્ર
    0.68
    explore
    0.68
    Activations Density 0.202%

    No Known Activations