© 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. 16-GEMMASCOPE-2-RES-262K
    7. 141438
    Prev
    Next
    INDEX
    Explanations

    dunes and skin

    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_16_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
     dist
    0.50
     Ministry
    0.49
    па
    0.47
     Ф
    0.46
    бри
    0.46
     factor
    0.45
     primarily
    0.45
    少量
    0.45
     topic
    0.44
    uras
    0.44
    POSITIVE LOGITS
    哳
    0.55
    ቱን
    0.54
     =-\
    0.53
    efois
    0.53
    لین
    0.52
    AllRef
    0.52
    Gonzalez
    0.52
    Enabled
    0.51
     उलट
    0.50
    EnableCOMDAT
    0.50
    Activations Density 0.000%

    No Known Activations