© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 5637
    Prev
    Next
    INDEX
    Explanations

    an error occurred

    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
     ansatz
    1.21
    穌
    1.18
    ToMany
    1.18
     Zeitraum
    1.13
    事务所
    1.11
     Mommy
    1.06
    cedores
    1.06
    CEEDINGS
    1.04
    到着
    1.03
    becue
    1.03
    POSITIVE LOGITS
    ře
    1.46
    yll
    1.39
    ř
    1.38
    rich
    1.35
    agn
    1.35
     buil
    1.34
    ρκ
    1.34
    的正
    1.33
    pering
    1.30
    スピード
    1.30
    Activations Density 0.043%

    No Known Activations