© 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. 11373
    Prev
    Next
    INDEX
    Explanations

    i get it

    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
     nhàng
    2.08
    ⌐
    1.94
     primaria
    1.88
    ただし
    1.85
     serez
    1.83
    ╥
    1.83
    र्थिक
    1.81
    PointerException
    1.81
    Outgoing
    1.78
     massima
    1.77
    POSITIVE LOGITS
    ürk
    1.79
    flap
    1.77
    hammer
    1.73
    issions
    1.71
    idar
    1.67
    rake
    1.66
     READER
    1.66
     러
    1.64
    𝐲
    1.61
    inking
    1.58
    Activations Density 0.000%

    No Known Activations