© 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. 1156
    Prev
    Next
    INDEX
    Explanations

    The followed by proper noun

    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
     en
    0.91
     in
    0.89
    IN
    0.89
     the
    0.89
     of
    0.86
     own
    0.84
    If
    0.83
     o
    0.83
     ο
    0.82
      
    0.81
    POSITIVE LOGITS
    atrical
    1.71
    odore
    1.50
    odora
    1.40
     Beatles
    1.39
    atres
    1.37
    ophylline
    1.33
    mselves
    1.32
    matic
    1.30
     Hague
    1.30
    orems
    1.28
    Activations Density 0.146%

    No Known Activations