© 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. 7-GEMMASCOPE-2-RES-16K
    7. 3649
    Prev
    Next
    INDEX
    Explanations

    more followed by quantity or attribute

    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_7_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
    τητα
    2.28
     variegated
    2.22
    
    2.13
    teis
    2.10
    chest
    2.03
    ground
    2.02
    도를
    2.01
    innings
    2.00
    ला
    1.98
    QUADS
    1.98
    POSITIVE LOGITS
    gató
    2.03
    с
    1.96
    ငယ်
    1.96
    ب
    1.91
    legraph
    1.91
     тру
    1.90
    درس
    1.89
    本文
    1.87
    Բ
    1.87
    =".$
    1.81
    Activations Density 0.075%

    No Known Activations