© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 209328
    Prev
    Next
    INDEX
    Explanations

    Philadelphia, babysitters, wearied

    np_acts-logits-general · gemini-2.5-flash-lite

    goals aligned

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     મિત
    0.47
     trà
    0.46
    歌曲
    0.45
    काश
    0.44
    स
    0.43
    хих
    0.43
    onimo
    0.43
    瀰
    0.43
    ཎ
    0.42
    ଈ
    0.42
    POSITIVE LOGITS
    t
    0.50
     cutters
    0.49
     Myrtle
    0.47
     windows
    0.44
    isations
    0.43
     fountains
    0.43
     zieht
    0.43
     unsett
    0.43
     ASD
    0.42
     La
    0.42
    Activations Density 0.001%

    No Known Activations