© 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. 1627
    Prev
    Next
    INDEX
    Explanations

    official websites and platforms

    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
    middlewares
    1.78
     perturbations
    1.72
    jač
    1.55
    大幅
    1.53
     perturbation
    1.53
    全員
    1.52
     batters
    1.51
    🎅
    1.50
     delimiter
    1.50
    ovaní
    1.50
    POSITIVE LOGITS
     websites
    2.22
     webpage
    2.18
     website
    2.16
     wikipedia
    2.05
    website
    2.05
     webpages
    1.96
     wiki
    1.96
    websites
    1.96
     Websites
    1.95
     Wikipedia
    1.89
    Activations Density 1.258%

    No Known Activations