© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 1077
    Prev
    Next
    INDEX
    Explanations

    street/road/avenue/station names

    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
    тивних
    1.37
    ANIES
    1.30
    多くの
    1.30
     Oldborough
    1.30
    έρα
    1.29
    ש
    1.29
    悆
    1.29
    ကြောင့်
    1.28
    ချုပ်
    1.28
    ORES
    1.27
    POSITIVE LOGITS
    ne
    1.73
     l
    1.70
     a
    1.55
    1
    1.55
    _
    1.54
    0
    1.53
     dati
    1.52
    m
    1.49
     iniz
    1.47
    .
    1.45
    Activations Density 0.580%

    No Known Activations