© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 56926
    Prev
    Next
    INDEX
    Explanations

    unrealistic and exaggerated

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

    artificial, unnatural, or robotic

    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_262k_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
     سون
    0.44
    Inline
    0.41
     decentralized
    0.40
    Helm
    0.40
     Multivariate
    0.40
    Otto
    0.39
    潢
    0.39
    提名
    0.39
     interwoven
    0.38
    FirstName
    0.38
    POSITIVE LOGITS
     unrealistic
    1.16
     unreal
    0.93
     exagger
    0.79
     exaggerated
    0.77
     exager
    0.77
     unnatural
    0.76
     exaggerate
    0.75
     artificial
    0.71
     exag
    0.71
     exaggeration
    0.70
    Activations Density 0.084%

    No Known Activations