© 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. 40-GEMMASCOPE-2-RES-16K
    7. 11453
    Prev
    Next
    INDEX
    Explanations

    famous people and their families

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

    specific names and places

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

    celebrity names

    np_max-act-logits · claude-4-5-sonnetTriggered by @sripadkarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_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
     રૂપ
    0.43
     கள
    0.42
     VOT
    0.41
     कैंपस
    0.41
     execute
    0.40
     manis
    0.39
     casse
    0.39
    깐
    0.39
     hine
    0.38
    guys
    0.37
    POSITIVE LOGITS
     TMZ
    0.53
     Sotheby
    0.49
     Versace
    0.48
     paparazzi
    0.48
     Berlusconi
    0.46
     figli
    0.44
     Sinatra
    0.43
     CNN
    0.41
    otheby
    0.40
     celebrity
    0.40
    Activations Density 0.396%

    No Known Activations