© 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. 218629
    Prev
    Next
    INDEX
    Explanations

    Results, New, Contract, numbers

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

    results in different languages

    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
    adeira
    0.46
    異なる
    0.46
    जो
    0.45
    জু
    0.45
    린
    0.44
    אי
    0.43
    拝
    0.43
    之为
    0.43
    ну
    0.42
    ”
    0.42
    POSITIVE LOGITS
    Results
    0.55
     思っ
    0.50
     заклад
    0.50
     allerdings
    0.48
     Results
    0.48
     ニュー
    0.47
     контракт
    0.47
     nooit
    0.46
     eigener
    0.46
     छह
    0.46
    Activations Density 0.001%

    No Known Activations