© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 30527
    Prev
    Next
    INDEX
    Explanations

    after initial buildsdeepening curiositiesfamous doorclosing carpets

    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
    لم
    0.55
    джер
    0.48
    利
    0.47
    seite
    0.47
    Телефон
    0.46
    ǎ
    0.45
    耐
    0.45
    فر
    0.43
    夏
    0.43
     roli
    0.42
    POSITIVE LOGITS
     Medic
    0.48
     Oregon
    0.47
     Medell
    0.46
     intrav
    0.45
     เพิ่ม
    0.45
     mineral
    0.45
     Medellín
    0.45
    "+"
    0.44
     vs
    0.44
    +"
    0.44
    Activations Density 0.001%

    No Known Activations