© 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. 6018
    Prev
    Next
    INDEX
    Explanations

    code definition and usage

    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
    effectiveness
    0.95
     વિ
    0.93
     tác
    0.91
    ˈ
    0.90
    স্ট্র
    0.84
     والش
    0.83
    Nom
    0.82
    =-\
    0.82
    brothers
    0.80
    Match
    0.80
    POSITIVE LOGITS
    前者
    1.54
    后者
    1.12
    дени
    0.94
     الاولى
    0.93
     latter
    0.91
    なさ
    0.90
    렜
    0.90
     recol
    0.90
    氐
    0.86
     jeep
    0.85
    Activations Density 0.276%

    No Known Activations