© 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. 126281
    Prev
    Next
    INDEX
    Explanations

    commands and instructions

    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
    ת
    0.49
    cond
    0.48
    training
    0.44
    dicke
    0.44
    bor
    0.43
    ೇಯ
    0.43
    arlight
    0.43
    פ
    0.43
    𝘁
    0.43
    theory
    0.42
    POSITIVE LOGITS
     mü
    0.52
     oğ
    0.51
    ,.
    0.48
    pertino
    0.47
    !}
    0.47
     dan
    0.47
     sampai
    0.46
     kecuali
    0.46
     splashed
    0.46
     XXI
    0.46
    Activations Density 0.003%

    No Known Activations