© 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-262K
    4. 7924
    Prev
    Next
    INDEX
    Explanations

    suffixes for nouns

    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_262k_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
    ни
    0.66
     his
    0.64
     informa
    0.62
    ن
    0.62
     estatal
    0.61
     apartheid
    0.61
    ו
    0.61
    ი
    0.61
     wodurch
    0.61
    یں
    0.60
    POSITIVE LOGITS
    ensor
    0.64
    ystem
    0.63
    ynchronous
    0.62
    ICK
    0.59
    creens
    0.59
    EARCH
    0.59
    ET
    0.58
     laterales
    0.58
    ızı
    0.57
    èques
    0.57
    Activations Density 0.110%

    No Known Activations