© 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. 130969
    Prev
    Next
    INDEX
    Explanations

    foreign or abstract concepts

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

    comparisons, updates, or configurations

    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
    ou
    0.48
    ia
    0.48
    á
    0.47
    Selen
    0.47
     രൂപ
    0.47
    iru
    0.46
     प्रसारण
    0.46
    More
    0.45
     Brig
    0.45
     نیا
    0.44
    POSITIVE LOGITS
     autochtones
    0.46
    哮
    0.44
    OOL
    0.44
     nontrivial
    0.42
     ottimo
    0.42
     manifeste
    0.42
     αι
    0.42
     adherence
    0.41
    OMA
    0.41
    ADER
    0.41
    Activations Density 0.000%

    No Known Activations