© 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. 5893
    Prev
    Next
    INDEX
    Explanations

    using libraries and frameworks

    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
    criteria
    0.93
     lieu
    0.90
     deference
    0.89
    ochial
    0.89
    tegr
    0.88
    ERTY
    0.87
    窥
    0.87
    irken
    0.86
    ywidual
    0.85
    ższe
    0.85
    POSITIVE LOGITS
     palette
    1.56
    NOWLEDGE
    1.55
     magicians
    1.51
     palettes
    1.48
     pectin
    1.48
     associative
    1.48
     Bundest
    1.48
     marshm
    1.45
    🎨
    1.43
    elephant
    1.43
    Activations Density 0.030%

    No Known Activations