© 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. 17486
    Prev
    Next
    INDEX
    Explanations

    built to last, years of use

    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
    جہاں
    0.44
     ლი
    0.43
    ποιή
    0.43
    ফোঁ
    0.41
     τρί
    0.40
     স্থষ্টি
    0.40
    ⅝
    0.40
     Fonction
    0.39
    msqrt
    0.39
     Gesellschaft
    0.39
    POSITIVE LOGITS
     stables
    0.48
    в
    0.47
     under
    0.43
    久
    0.40
    Pos
    0.40
     gym
    0.40
    稳定
    0.40
     arbe
    0.40
     without
    0.39
     above
    0.39
    Activations Density 0.005%

    No Known Activations