© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 1039
    Prev
    Next
    INDEX
    Explanations

    has/had been

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     मांझी
    1.46
    iendo
    1.30
    ać
    1.30
     ľud
    1.29
    iato
    1.29
    ps
    1.27
    iya
    1.27
    鈁
    1.26
    하다
    1.25
     Czę
    1.25
    POSITIVE LOGITS
    á
    1.38
    েন
    1.19
    ,
    1.17
     huwa
    1.12
    ana
    1.07
     overcoming
    1.00
     renders
    0.99
     intending
    0.97
    は大
    0.96
    ll
    0.96
    Activations Density 0.052%

    No Known Activations