© 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. 181190
    Prev
    Next
    INDEX
    Explanations

    piece, Roll, SM, low, provide, schools

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

    counterintuitive phrases

    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
    橙
    0.47
    мі
    0.46
    มิ
    0.44
     pyautogui
    0.44
    芨
    0.44
    部
    0.43
    кі
    0.43
    葡萄
    0.42
    羡
    0.42
     angg
    0.41
    POSITIVE LOGITS
     komma
    0.49
     devolution
    0.49
    essä
    0.48
     سعر
    0.48
     Performs
    0.47
     Conventional
    0.46
    쇠
    0.45
    reduction
    0.45
    inner
    0.45
     Cradle
    0.45
    Activations Density 0.000%

    No Known Activations