© 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. 110841
    Prev
    Next
    INDEX
    Explanations

    non-English words or specific phrases

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

    safety, acts, historical context

    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
    ঞ্জ
    0.48
     Convert
    0.46
    Disabled
    0.46
     গ্রহণ
    0.45
     Siles
    0.45
    ্যাক
    0.45
    fort
    0.42
    凿
    0.42
     Straight
    0.41
     physicochemical
    0.40
    POSITIVE LOGITS
    ลม
    0.48
     lycée
    0.47
     nyc
    0.47
     анализа
    0.45
     análise
    0.45
     város
    0.45
     общения
    0.44
     anál
    0.44
     começou
    0.44
     índices
    0.44
    Activations Density 0.001%

    No Known Activations