© 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. 4864
    Prev
    Next
    INDEX
    Explanations

    journal citations and DOIs

    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
    ACTER
    1.81
     derogatory
    1.52
    -*/
    1.49
     *"
    1.43
    uminescent
    1.39
    antiation
    1.39
     cathodic
    1.36
    эффици
    1.36
    alamy
    1.35
     INCIDENTAL
    1.35
    POSITIVE LOGITS
     musim
    1.55
    寢
    1.49
    纽
    1.48
     fosse
    1.48
    盡
    1.41
    绝
    1.40
    鐙
    1.38
     hacerlo
    1.38
    去
    1.38
    尽
    1.37
    Activations Density 0.131%

    No Known Activations