© 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. 58935
    Prev
    Next
    INDEX
    Explanations

    keto flu and agony

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

    negative experiences and suffering

    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
     እድ
    0.46
    Opportunity
    0.44
     നടക്കുന്ന
    0.44
    窃
    0.44
    土地
    0.44
    Opportun
    0.43
    ክል
    0.43
    Shroud
    0.43
    צי
    0.42
    矢
    0.42
    POSITIVE LOGITS
     discomfort
    1.14
     uncomfortable
    0.98
     intolerable
    0.86
     불편
    0.86
     unbearable
    0.81
    痛苦
    0.79
     intoler
    0.74
     disliked
    0.73
     painful
    0.72
     douleurs
    0.72
    Activations Density 0.070%

    No Known Activations