© 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. 13-GEMMASCOPE-2-RES-16K
    7. 869
    Prev
    Next
    INDEX
    Explanations

    rating intensity of feelings

    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_13_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
     Júnior
    0.98
    Iddict
    0.97
     Michael
    0.95
     মিলিয়ন
    0.94
     जूनियर
    0.93
     Kevin
    0.93
     रघु
    0.93
    维
    0.93
     Birds
    0.93
     John
    0.92
    POSITIVE LOGITS
     ervoor
    1.08
     antennis
    1.04
     procure
    1.04
     initialization
    1.01
     debugging
    0.98
     detect
    0.98
     adsorbent
    0.97
    separator
    0.96
    detector
    0.96
    sql
    0.96
    Activations Density 0.309%

    No Known Activations