© 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. 126274
    Prev
    Next
    INDEX
    Explanations

    LinkedIn profile related information

    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
    o
    0.50
     parrot
    0.49
    ed
    0.48
    ing
    0.46
     parrots
    0.46
     მხოლოდ
    0.44
    ס
    0.44
    extreme
    0.43
    anish
    0.43
    ermost
    0.42
    POSITIVE LOGITS
    伈
    0.57
    CIES
    0.49
    cké
    0.47
     comptes
    0.46
    ঘাত
    0.46
    靕
    0.45
     linéaire
    0.44
    致力于
    0.44
    চিক
    0.44
    穿着
    0.43
    Activations Density 0.003%

    No Known Activations