© 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. 13-GEMMASCOPE-2-RES-16K
    7. 13836
    Prev
    Next
    INDEX
    Explanations

    quoted speech attribution

    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
     גע
    1.15
     «
    1.00
     Santi
    1.00
     mixte
    0.98
     (+
    0.94
    Nike
    0.92
    преки
    0.92
     Liss
    0.92
     заду
    0.91
     nuo
    0.91
    POSITIVE LOGITS
     formContext
    1.32
     underpinning
    1.10
     demonstrations
    1.07
     authentication
    1.03
    㴦
    1.03
     ይሰ
    1.02
    㳳
    1.02
     واحد
    1.01
     beside
    0.98
     attachment
    0.98
    Activations Density 0.046%

    No Known Activations