© 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. 136768
    Prev
    Next
    INDEX
    Explanations

    main category, most complete, stock storage

    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
    ал
    0.47
    걀
    0.46
     После
    0.44
    面试
    0.44
    য়োজনীয়
    0.42
    祷
    0.41
     관련된
    0.41
     Spirituality
    0.41
     跟
    0.41
     推
    0.40
    POSITIVE LOGITS
    بيق
    0.45
    ewhat
    0.44
     observers
    0.43
     platform
    0.43
     contre
    0.42
    ით
    0.42
     Clube
    0.42
    ịnh
    0.42
    Observers
    0.41
     economic
    0.41
    Activations Density 0.001%

    No Known Activations