© 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. 10295
    Prev
    Next
    INDEX
    Explanations

    this means

    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
    𝗗
    0.54
    Ტ
    0.44
    今後
    0.44
     також
    0.43
     더욱
    0.42
     અન્ય
    0.42
    ależy
    0.42
    अन्य
    0.42
    笉
    0.42
     будет
    0.41
    POSITIVE LOGITS
     meaning
    0.43
     firstly
    0.38
      
    0.37
     (
    0.37
     pertama
    0.37
     veins
    0.37
     first
    0.36
    اور
    0.36
    -
    0.35
     unfamiliar
    0.35
    Activations Density 0.196%

    No Known Activations