© 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. 10466
    Prev
    Next
    INDEX
    Explanations

    chrono, chroma, chords, chimeras

    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
     কর্তৃক
    1.18
     র‌্যা
    0.96
     Пре
    0.93
     총
    0.93
     품
    0.92
     상세
    0.92
    objClass
    0.91
     વિશે
    0.91
     변경
    0.90
     নির্মিত
    0.89
    POSITIVE LOGITS
     fuck
    1.42
     fucking
    1.36
    HAHA
    1.30
     bullshit
    1.26
     assh
    1.26
    😂😂
    1.23
     shitty
    1.22
    😂
    1.20
     lol
    1.20
     stupid
    1.19
    Activations Density 0.040%

    No Known Activations