© 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. 24537
    Prev
    Next
    INDEX
    Explanations

    not much

    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
    culus
    0.45
    itsyn
    0.45
    ى
    0.44
     الا
    0.44
     keď
    0.44
     elsewhere
    0.44
    醀
    0.44
    茷
    0.43
     Україн
    0.41
    üman
    0.41
    POSITIVE LOGITS
     upkeep
    0.48
     warmth
    0.46
    jpg
    0.44
    すぐに
    0.43
     lungs
    0.40
     crimes
    0.40
    ән
    0.40
     oxidative
    0.39
    𝜇
    0.39
    诟
    0.39
    Activations Density 0.001%

    No Known Activations