© 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. 99653
    Prev
    Next
    INDEX
    Explanations

    goal assessment and breakdown

    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
     Centres
    0.44
     Centre
    0.43
     Mum
    0.42
     Engineered
    0.42
     but
    0.42
     (
    0.41
    ie
    0.41
     shortcuts
    0.41
    Engine
    0.40
     freeway
    0.40
    POSITIVE LOGITS
     думать
    0.51
    notlocked
    0.47
     Шев
    0.46
     డౌ
    0.45
    ні
    0.44
     möglicherweise
    0.44
     ಡೇ
    0.44
     Бре
    0.43
    ელი
    0.42
    烀
    0.42
    Activations Density 0.006%

    No Known Activations