© 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. 13-GEMMASCOPE-2-RES-16K
    7. 5213
    Prev
    Next
    INDEX
    Explanations

    however, I want to

    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_13_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
     reduc
    1.33
     usp
    1.32
    ar
    1.25
    ig
    1.22
     nou
    1.22
    r
    1.22
    ತ್ರಿ
    1.22
    ಝ
    1.21
     fij
    1.21
     pak
    1.21
    POSITIVE LOGITS
     Expressions
    1.99
    SalesReport
    1.90
    CQL
    1.86
    ProgressListener
    1.80
    وون
    1.72
    इजेशन
    1.67
    <unused349>
    1.66
     Oldborough
    1.66
    ControlButton
    1.65
     Creations
    1.64
    Activations Density 0.159%

    No Known Activations