© 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. 2559
    Prev
    Next
    INDEX
    Explanations

    emphasizing traits or outcomes

    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
    setScene
    1.37
    Registre
    1.22
     HttpResponse
    1.18
     PATRIOT
    1.16
    ISTA
    1.14
     Expedia
    1.10
     regista
    1.09
    འ
    1.09
    istu
    1.06
    FLP
    1.05
    POSITIVE LOGITS
     Birk
    1.15
     nash
    1.08
    kait
    1.08
    парт
    1.04
    kol
    1.03
    žių
    1.03
    ikal
    1.02
     dal
    1.00
    วก
    0.98
    iko
    0.97
    Activations Density 0.088%

    No Known Activations