© 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-65K
    7. 4345
    Prev
    Next
    INDEX
    Explanations

    integration strategies

    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_65k_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
    Kui
    0.52
    Mile
    0.48
     ٹک
    0.45
    开源
    0.45
    Silk
    0.44
    ７
    0.44
    ٽ
    0.43
    Sak
    0.43
    Ნ
    0.43
    Aly
    0.42
    POSITIVE LOGITS
     परिचालन
    0.52
    j
    0.50
     चतु
    0.48
    ियों
    0.46
    කාශ
    0.46
     звуча
    0.45
     queridos
    0.45
     neder
    0.45
     elimin
    0.45
    unication
    0.44
    Activations Density 0.016%

    No Known Activations