© 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. 125905
    Prev
    Next
    INDEX
    Explanations

    verify check 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
    妬
    0.50
     vattum
    0.47
    滸
    0.47
     वित्त
    0.46
    轅
    0.46
     खर्चा
    0.45
    ivg
    0.45
    ୪
    0.45
    鏢
    0.44
    いずれ
    0.44
    POSITIVE LOGITS
     World
    0.52
     Secret
    0.50
     to
    0.47
    el
    0.47
     portug
    0.46
     a
    0.46
     is
    0.46
     Space
    0.46
    key
    0.46
    டும்
    0.46
    Activations Density 0.001%

    No Known Activations