© 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. 1880
    Prev
    Next
    INDEX
    Explanations

    indexing variables

    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
    y
    0.96
    l
    0.95
     AsyncTask
    0.92
    uZ
    0.89
    oises
    0.89
     nltk
    0.83
    u
    0.82
     `=
    0.82
     Riot
    0.78
    وظ
    0.78
    POSITIVE LOGITS
    िल्या
    0.77
    ordon
    0.73
    oun
    0.71
    endor
    0.69
    üb
    0.67
     دفاتر
    0.67
     कां
    0.66
     fixation
    0.64
     landmark
    0.63
    ambers
    0.63
    Activations Density 0.356%

    No Known Activations