© 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. 15727
    Prev
    Next
    INDEX
    Explanations

    version keeping

    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
    collapsed
    1.51
     सब्जी
    1.50
    欳
    1.49
    grilled
    1.48
    㤟
    1.47
    calup
    1.46
     subtly
    1.45
     неста
    1.43
    Another
    1.42
    晠
    1.42
    POSITIVE LOGITS
    embedding
    0.91
     engagements
    0.89
    <i>
    0.88
     dan
    0.88
     কাগজ
    0.84
    schemas
    0.84
     jam
    0.83
    osha
    0.82
    ikti
    0.81
    orsch
    0.80
    Activations Density 0.000%

    No Known Activations