© 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. 4911
    Prev
    Next
    INDEX
    Explanations

    technical terms and lists

    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
     titular
    2.28
     publisher
    2.25
    今年
    2.17
    あす楽
    2.04
     unpublished
    2.03
     ninety
    2.02
    .]
    2.01
    ][
    2.01
    .|
    2.01
     eighty
    2.01
    POSITIVE LOGITS
    ensitivity
    1.63
    愆
    1.53
    пів
    1.49
    ostrat
    1.43
    istics
    1.42
     Quotient
    1.41
    ocyte
    1.40
    ettings
    1.39
    istika
    1.39
    愍
    1.38
    Activations Density 0.077%

    No Known Activations