© 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. 81638
    Prev
    Next
    INDEX
    Explanations

    lists with varying concepts

    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
    tong
    0.58
    nt
    0.55
    at
    0.53
     nightclubs
    0.53
    sor
    0.50
    nh
    0.49
    ਾ
    0.49
     on
    0.48
    he
    0.47
    ێنی
    0.47
    POSITIVE LOGITS
     רי
    0.47
     ভুল
    0.46
    かもしれませんが
    0.46
     कांसेप्ट
    0.45
     retire
    0.45
     пен
    0.44
     তৃতীয়
    0.44
     ファイル
    0.44
    InCM
    0.44
     DataType
    0.44
    Activations Density 0.001%

    No Known Activations