© 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. 7-GEMMASCOPE-2-RES-16K
    7. 12555
    Prev
    Next
    INDEX
    Explanations

    arboreal, binomial, ad hoc

    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
    <unused794>
    3.07
    <unused837>
    3.01
    <unused995>
    3.00
    Произ
    2.99
    <unused830>
    2.98
     nCharString
    2.90
    <unused750>
    2.90
    <unused822>
    2.88
    <unused58>
    2.88
    <unused826>
    2.87
    POSITIVE LOGITS
    i
    2.94
    es
    2.92
    <bos>
    2.91
    en
    2.70
    y
    2.16
    el
    2.00
    ening
    1.87
    core
    1.86
    dl
    1.86
    ri
    1.86
    Activations Density 0.010%

    No Known Activations