© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14418
    Prev
    Next
    INDEX
    Explanations

    shapes him, essential to American, attitudes as, name of science, controversy that

    np_acts-logits-general · gemini-2.5-flash-lite

    history and transformative events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Boyfriend
    0.71
     mujhe
    0.62
     xD
    0.61
     lmao
    0.61
     idk
    0.60
     🥰
    0.59
     haha
    0.59
    没办法
    0.59
     😂
    0.58
    😭😭
    0.58
    POSITIVE LOGITS
    histor
    0.46
    probable
    0.46
    tembre
    0.45
     unmistakable
    0.45
     triumphant
    0.44
    mainframe
    0.44
    princip
    0.44
     boreal
    0.44
     peruse
    0.44
    sailboat
    0.43
    Activations Density 0.009%

    No Known Activations