© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 8414
    Prev
    Next
    INDEX
    Explanations

    4. followed by a category

    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
     번째
    1.02
     nullable
    0.99
     ವಿರುದ್ಧ
    0.98
     ござい
    0.96
     maxHeight
    0.96
     się
    0.96
     minY
    0.95
     ​​
    0.95
     sich
    0.95
     borderColor
    0.94
    POSITIVE LOGITS
    5
    3.05
    6
    3.03
    4
    3.02
    7
    2.99
    8
    2.96
    9
    2.91
    3
    2.89
    2
    2.65
    1
    2.41
    ５
    2.26
    Activations Density 0.195%

    No Known Activations