© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 15626
    Prev
    Next
    INDEX
    Explanations

    positive/negative connotation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
     বোঝার
    0.66
    oclaw
    0.60
     enemigo
    0.55
    ayeva
    0.55
    ỗ
    0.55
    庴
    0.55
    般的
    0.54
     समझने
    0.53
    ಮೆ
    0.53
    ozzi
    0.53
    POSITIVE LOGITS
     vibes
    1.09
     (+)
    1.04
     (-)
    1.03
     reinforcement
    1.02
     affirmations
    0.98
     affirmation
    0.97
     feedback
    0.95
     connotation
    0.94
     externalities
    0.92
    (-)
    0.87
    Activations Density 0.038%

    No Known Activations