© 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. 989
    Prev
    Next
    INDEX
    Explanations

    name, occupation, or nationality

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

    contrastive conjunctions

    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
     Arts
    0.47
    ни
    0.46
     Rid
    0.45
    usk
    0.43
     Fragments
    0.43
     ALLOYS
    0.41
    散
    0.41
    Arts
    0.40
    1
    0.40
     cui
    0.39
    POSITIVE LOGITS
     કર્મચારી
    0.45
     اکثر
    0.45
    ܠܐ
    0.44
    это
    0.43
    ترین
    0.43
     conteú
    0.43
     ऑफिसर
    0.42
    volent
    0.42
    स्ती
    0.41
     पाकिस्तानी
    0.41
    Activations Density 0.000%

    No Known Activations