© 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. 203259
    Prev
    Next
    INDEX
    Explanations

    senator and ministerial titles

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

    not having lived experience

    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
     영국
    0.48
    ępow
    0.46
     బిల్
    0.45
     Hertfordshire
    0.45
    葡
    0.45
    房屋
    0.43
    Scotland
    0.42
     सार्थक
    0.42
    영상
    0.42
     नाट
    0.41
    POSITIVE LOGITS
     doigts
    0.46
     irmãos
    0.42
     る
    0.42
     pads
    0.41
     amar
    0.41
     frères
    0.41
     qualcosa
    0.41
     quei
    0.41
     aby
    0.40
     вересня
    0.40
    Activations Density 0.002%

    No Known Activations