© 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. 138050
    Prev
    Next
    INDEX
    Explanations

    news, legends, indicators, team

    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
    𝐠
    0.45
     زبان
    0.44
    𝐜
    0.44
    de
    0.43
     نار
    0.43
     ఒక్క
    0.41
     anthropologist
    0.41
     اخ
    0.41
     Manip
    0.41
     الأوروب
    0.41
    POSITIVE LOGITS
    ংস
    0.51
    UnderTest
    0.51
     actualidad
    0.50
    า
    0.49
     quella
    0.47
    П
    0.46
    Ꮂ
    0.45
    ᱷ
    0.45
    ҳа
    0.44
     cultivated
    0.44
    Activations Density 0.000%

    No Known Activations