© 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. 6371
    Prev
    Next
    INDEX
    Explanations

    object property access

    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
    .
    2.43
    .​
    2.41
    .(
    2.35
    .?
    2.32
    .[
    2.23
    .—
    2.16
    ._
    2.12
    ​.
    2.10
    .¹
    2.09
    .--
    2.08
    POSITIVE LOGITS
    すすめ
    1.60
    膳
    1.52
    깐
    1.47
    јединачна
    1.44
    کرد
    1.43
    цата
    1.43
     rozm
    1.41
    坯
    1.39
    場面積
    1.38
     должна
    1.37
    Activations Density 0.001%

    No Known Activations