© 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. 3475
    Prev
    Next
    INDEX
    Explanations

    computational methods and tools

    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
    ystick
    1.65
    毬
    1.59
    由於
    1.55
    збеки
    1.52
    уд
    1.51
    eta
    1.47
     provoqu
    1.46
    =":
    1.46
     inputStream
    1.45
     piu
    1.44
    POSITIVE LOGITS
    ridor
    1.12
     подхода
    1.05
    approach
    1.05
     conhecimento
    1.03
     approaches
    1.01
     approach
    1.01
     knowledge
    0.99
    excellence
    0.99
     conocimientos
    0.96
     kennis
    0.96
    Activations Density 0.219%

    No Known Activations