© 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. 3582
    Prev
    Next
    INDEX
    Explanations

    innovative and creative approaches

    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
     Aless
    1.05
    Aless
    0.92
    i
    0.86
     Ingles
    0.83
    ieniem
    0.82
    inj
    0.82
    エン
    0.82
    in
    0.82
    u
    0.81
    Bene
    0.80
    POSITIVE LOGITS
     countdown
    1.65
    규모
    1.50
     nonstop
    1.43
    ziff
    1.43
     siting
    1.42
    щиков
    1.41
     dialed
    1.41
     WPF
    1.39
     committees
    1.38
     televised
    1.37
    Activations Density 0.067%

    No Known Activations