© 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. 34956
    Prev
    Next
    INDEX
    Explanations

    funny personal actions/traits

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

    playful and cheeky messages

    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
     comorbid
    0.49
     insofar
    0.47
    Fuck
    0.44
     unsatisf
    0.44
     manifestly
    0.43
     profoundly
    0.42
     percept
    0.42
    엷
    0.41
     ಕಂಪ
    0.40
     metast
    0.40
    POSITIVE LOGITS
     hilarious
    1.03
     jokingly
    1.02
     😂😂
    0.91
     joked
    0.90
     cheeky
    0.89
     mischievous
    0.89
    搞笑
    0.86
     playfully
    0.86
    😂😂
    0.85
    😂
    0.83
    Activations Density 0.074%

    No Known Activations