© 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. 169865
    Prev
    Next
    INDEX
    Explanations

    location names and engineering

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

    open weights

    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
    hemeral
    0.47
     אטאטורק
    0.45
    여기
    0.44
     recogida
    0.42
    🏛
    0.41
    ORIENT
    0.40
    arrive
    0.40
    ｜
    0.40
    avacak
    0.39
    面白い
    0.38
    POSITIVE LOGITS
     Dayton
    0.45
     इंजीनियरिंग
    0.45
     Engineer
    0.44
     Warranty
    0.44
    ंबू
    0.44
     বাধ
    0.43
     Bend
    0.43
     kullan
    0.42
     използ
    0.42
     Engineering
    0.42
    Activations Density 0.002%

    No Known Activations