© 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. 144527
    Prev
    Next
    INDEX
    Explanations

    which translates to

    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
    ὄ
    0.48
     পরিস্থিতি
    0.46
    OnChange
    0.46
    ὃ
    0.45
     indivíduos
    0.45
    логі
    0.44
    слары
    0.43
    ὤ
    0.43
     дея
    0.43
     тяж
    0.43
    POSITIVE LOGITS
     near
    0.56
    ක්
    0.47
     satin
    0.47
     Saturday
    0.46
     Honey
    0.46
     honed
    0.45
     honey
    0.45
     Nim
    0.44
     Lua
    0.44
     Satin
    0.44
    Activations Density 0.008%

    No Known Activations