© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 5220
    Prev
    Next
    INDEX
    Explanations

    negative emotions and states

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

    anxiety and negative emotions

    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
    XEL
    0.38
     தொழில்நுட்ப
    0.38
    HOUSE
    0.38
     служба
    0.35
     সম্পন্ন
    0.34
    街
    0.34
    楎
    0.34
    OSPHER
    0.33
    緎
    0.33
     তান
    0.33
    POSITIVE LOGITS
     lament
    0.73
     dismay
    0.73
     bemo
    0.73
     panicked
    0.71
     wondering
    0.69
     worried
    0.68
     shocked
    0.68
     despair
    0.68
     nervously
    0.68
     horrified
    0.67
    Activations Density 0.401%

    No Known Activations