© 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. 5153
    Prev
    Next
    INDEX
    Explanations

    return statements

    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
    querdo
    1.60
    헛
    1.46
    MouseButton
    1.44
     beatae
    1.43
     Жа
    1.39
    쬐
    1.39
     Espagne
    1.38
    _{-}\
    1.37
     Martinez
    1.35
     Aguil
    1.35
    POSITIVE LOGITS
     яку
    1.81
    army
    1.50
     epiz
    1.50
     anesthesia
    1.50
    shi
    1.49
    buch
    1.49
     zain
    1.48
    ytocin
    1.48
    fect
    1.47
    ichiro
    1.46
    Activations Density 0.000%

    No Known Activations