© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 4350
    Prev
    Next
    INDEX
    Explanations

    attract and retain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     prefixed
    0.75
    stanza
    0.71
    clipped
    0.70
    framed
    0.64
     episod
    0.60
    ↘
    0.59
     alleine
    0.59
     mainline
    0.59
    billed
    0.58
     shillings
    0.57
    POSITIVE LOGITS
     suppliers
    2.07
    suppliers
    1.94
     Supplier
    1.92
    硌
    1.86
     supplier
    1.85
    uesa
    1.83
    igues
    1.82
     Suppliers
    1.80
     arbitrator
    1.79
     Agn
    1.73
    Activations Density 0.149%

    No Known Activations