© 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. 4317
    Prev
    Next
    INDEX
    Explanations

    goals and aspirations

    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
    \%).
    1.27
    \%)
    1.20
    pend
    1.13
     %).
    1.12
     %)
    1.09
    leine
    1.09
    mages
    1.08
     dyd
    1.08
    $/.
    1.08
     %),
    1.07
    POSITIVE LOGITS
    ivne
    1.26
     retrato
    1.20
     المز
    1.18
    ították
    1.17
     IActionResult
    1.17
    ukun
    1.16
     renversement
    1.16
    ovjek
    1.15
     REPRESENT
    1.15
    彫
    1.13
    Activations Density 0.040%

    No Known Activations