© 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. 53154
    Prev
    Next
    INDEX
    Explanations

    specific phrases and their continuations

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

    list of foreign city names

    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
     meestal
    0.44
    鎶
    0.43
    类似于
    0.43
    tìm
    0.43
     সমন্বয়
    0.42
     تطبيق
    0.42
    鏁
    0.42
    考验
    0.41
     преимуще
    0.41
     комі
    0.41
    POSITIVE LOGITS
     Estelle
    0.52
     Gemeinde
    0.46
     durante
    0.46
     Dates
    0.45
     Przed
    0.45
     during
    0.45
     JJ
    0.43
     Pflanzen
    0.43
     }
    0.42
     Bruno
    0.42
    Activations Density 0.000%

    No Known Activations