© 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. 0
    Prev
    Next
    INDEX
    Explanations

    positive emotions and care

    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
     उपभोक्ताओं
    1.09
     상당히
    1.09
     eficiente
    1.05
    Faction
    1.04
    잽
    1.03
    绩效
    1.03
     효율
    1.03
    生成的
    1.02
     측정
    1.02
     taxonomy
    1.01
    POSITIVE LOGITS
     grieve
    1.57
     heartache
    1.52
     loving
    1.46
     grieving
    1.46
    💔
    1.45
     hugs
    1.45
     heartbreak
    1.41
     unconditional
    1.40
     sorrow
    1.38
     loved
    1.37
    Activations Density 4.070%

    No Known Activations