© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11951
    Prev
    Next
    INDEX
    Explanations

    updating, said, late, essential, consequence

    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
     તેમજ
    0.57
    and
    0.55
     तसेच
    0.54
    และ
    0.49
    Atlantic
    0.45
    ＆
    0.45
     તથા
    0.44
     և
    0.44
     ਅਤੇ
    0.44
     tudi
    0.43
    POSITIVE LOGITS
     formulae
    0.42
     artiste
    0.40
    制品
    0.40
     suddenly
    0.40
     spokesman
    0.39
     artistes
    0.39
     kellett
    0.38
     administrator
    0.37
     benefactor
    0.37
     advertiser
    0.36
    Activations Density 0.006%

    No Known Activations