© 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. 6692
    Prev
    Next
    INDEX
    Explanations

    choices and options

    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
    hyung
    2.21
    ison
    2.10
     standards
    2.06
    ayers
    2.04
    chant
    1.96
    main
    1.90
    Dirty
    1.90
    𝚒
    1.89
    ียบ
    1.89
    ding
    1.89
    POSITIVE LOGITS
     فرص
    1.68
     iesp
    1.65
     afforded
    1.63
    pportun
    1.62
     Angebote
    1.59
     opportunità
    1.56
    MenuStrip
    1.55
    pportunities
    1.54
    offerta
    1.53
     OPPORT
    1.52
    Activations Density 0.122%

    No Known Activations