© 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. 203696
    Prev
    Next
    INDEX
    Explanations

    engaged with/refuses to/be largest/color LEDs/side of the road

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

    predicting instead of understanding

    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
    比較的
    0.49
     کدام
    0.47
    ın
    0.46
    ør
    0.46
    nicht
    0.46
    겹
    0.46
     nicht
    0.44
     قائمة
    0.44
     독일
    0.44
     낮은
    0.43
    POSITIVE LOGITS
    部落
    0.47
    anthin
    0.47
    iential
    0.47
    рте
    0.46
    NQ
    0.46
    т
    0.45
    ट्र
    0.45
    р
    0.45
    ртов
    0.44
     Kipling
    0.44
    Activations Density 0.000%

    No Known Activations