© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7378
    Prev
    Next
    INDEX
    Explanations

    preparing or listing examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     do
    0.91
    пад
    0.88
     no
    0.85
     nuestro
    0.85
     scritta
    0.83
    о
    0.80
     vốn
    0.80
     nuestra
    0.76
     থাক
    0.76
     propietario
    0.76
    POSITIVE LOGITS
     enhanced
    1.11
     incubated
    1.07
    enhanced
    1.06
    扡
    1.03
     التحكم
    1.00
     improved
    1.00
    mob
    0.98
     enthalpies
    0.98
     wheels
    0.98
    აწილ
    0.98
    Activations Density 0.003%

    No Known Activations