© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3679
    Prev
    Next
    INDEX
    Explanations

    self-control and understanding oneself

    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
     Carnegie
    1.46
    ropolitan
    1.43
     Marcin
    1.40
     scattering
    1.38
    ~~~~~~~~
    1.35
     together
    1.32
     Johannesburg
    1.30
     -------------
    1.30
     Picker
    1.27
    chrome
    1.26
    POSITIVE LOGITS
    neg
    1.25
     subpar
    1.22
    RQ
    1.17
     unworthy
    1.11
     괜
    1.10
    別人
    1.08
    ethylamine
    1.08
     ignores
    1.08
    我不
    1.06
    devi
    1.06
    Activations Density 0.087%

    No Known Activations