© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 75190
    Prev
    Next
    INDEX
    Explanations

    remove unnecessary phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kilos
    0.43
     surroundings
    0.40
    мни
    0.40
     drugstore
    0.40
     fridge
    0.39
     odk
    0.39
     chợ
    0.38
    傘
    0.38
    硐
    0.38
    鉢
    0.38
    POSITIVE LOGITS
    avení
    0.43
    ális
    0.43
     国家
    0.43
    였습니다
    0.43
     वसू
    0.42
     பொய்ய
    0.42
    ußen
    0.42
    اهرة
    0.41
    lessons
    0.41
    ployment
    0.41
    Activations Density 0.009%

    No Known Activations