© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 26
    Prev
    Next
    INDEX
    Explanations

    interest and desire

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_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
    <unused18>
    1.03
     коммуника
    0.98
     обще
    0.95
    erta
    0.95
    <unused24>
    0.95
     კონ
    0.92
     предостав
    0.92
     क़ुर्आन
    0.92
    <unused16>
    0.92
    氻
    0.92
    POSITIVE LOGITS
     love
    1.87
     loves
    1.67
     LOVE
    1.61
    love
    1.56
     Love
    1.52
     loving
    1.50
     fondness
    1.44
    Love
    1.41
    LOVE
    1.38
     사랑
    1.37
    Activations Density 2.084%

    No Known Activations