© 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. 1676
    Prev
    Next
    INDEX
    Explanations

    for clarity or easier browsing

    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
    ‒
    2.23
    ――
    2.06
    ​—
    2.02
    ”—
    1.99
     —,
    1.95
     –,
    1.90
    ―
    1.86
    ⁠
    1.85
    ‑
    1.79
    ,»
    1.79
    POSITIVE LOGITS
     ppl
    2.82
     shit
    2.16
     yg
    2.01
     đc
    1.99
    ㅄ
    1.91
     crap
    1.85
     fuck
    1.80
     fucking
    1.78
     guy
    1.76
     ****
    1.76
    Activations Density 1.248%

    No Known Activations