© 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. 6463
    Prev
    Next
    INDEX
    Explanations

    psychological states and descriptions

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

    social, philosophy, psychological concepts

    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
     Canva
    0.40
     ২০১৯
    0.38
     আজকে
    0.38
     OnePlus
    0.38
     nyata
    0.37
     chặn
    0.37
     newline
    0.36
    劻
    0.36
     zásobníku
    0.36
     ২০২১
    0.36
    POSITIVE LOGITS
     psychological
    0.62
     psychologically
    0.55
    心理
    0.50
     психологи
    0.49
     sociological
    0.47
     emotionally
    0.47
     психо
    0.47
     Psychological
    0.46
     mensch
    0.46
     emotional
    0.44
    Activations Density 0.095%

    No Known Activations