© 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. 10373
    Prev
    Next
    INDEX
    Explanations

    general knowledge disclaimers

    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
    🫐
    1.11
    🫂
    1.07
    🪄
    1.03
    🫣
    0.98
    🫡
    0.95
    ້າ
    0.94
     vrsta
    0.93
    🫶
    0.91
    🥹
    0.90
     LIC
    0.90
    POSITIVE LOGITS
    اي
    0.90
     Matthews
    0.88
    http
    0.86
     http
    0.85
    ttp
    0.85
     dwindling
    0.82
     inconclusive
    0.81
     ਘ
    0.80
     tweets
    0.80
     tweeted
    0.79
    Activations Density 0.104%

    No Known Activations