© 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. 10169
    Prev
    Next
    INDEX
    Explanations

    choose the one

    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
     及
    1.41
     लिहाजा
    1.32
     inmue
    1.27
     iaitu
    1.27
    嬗
    1.24
     standardised
    1.24
     தமது
    1.21
    迨
    1.21
     motorised
    1.20
     கலங்கரை
    1.20
    POSITIVE LOGITS
     ഞാൻ
    0.79
    悪い
    0.78
    icolor
    0.74
    フル
    0.71
     Topeka
    0.71
     Walla
    0.70
    的东西
    0.69
     Thinking
    0.68
    ⇣
    0.68
    וא
    0.68
    Activations Density 0.227%

    No Known Activations