© 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. 4049
    Prev
    Next
    INDEX
    Explanations

    model programming, technical, medical

    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
    </blockquote>
    1.34
    </
    1.19
    ><
    1.13
     gypsum
    1.12
    »
    1.09
    marès
    1.07
    цията
    1.07
    «
    1.06
     />
    1.05
    spre
    1.03
    POSITIVE LOGITS
    itoral
    1.38
    แตก
    1.29
    亠
    1.28
    𝐤
    1.22
    manifold
    1.16
    ksam
    1.15
    zimmer
    1.15
     кеңсеси
    1.14
    KINS
    1.14
     contentType
    1.14
    Activations Density 0.071%

    No Known Activations