© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 126084
    Prev
    Next
    INDEX
    Explanations

    if an

    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
    Q
    0.46
    nama
    0.44
    cej
    0.41
    vable
    0.41
    htt
    0.40
    tim
    0.40
     lulus
    0.40
     ilang
    0.40
    力
    0.40
     name
    0.39
    POSITIVE LOGITS
     הצ
    0.50
     dérivés
    0.49
     निरंतर
    0.48
     quirúrg
    0.46
     ಇದನ್ನು
    0.46
     insurgents
    0.45
     dirigés
    0.45
     बजरंग
    0.45
     성
    0.45
     disfrutar
    0.44
    Activations Density 0.005%

    No Known Activations