© 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. 3485
    Prev
    Next
    INDEX
    Explanations

    wide range

    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
    ل
    1.60
     fumes
    1.30
     upbeat
    1.19
     barbec
    1.19
     butane
    1.18
     adjour
    1.15
     frequ
    1.13
     storms
    1.13
    الي
    1.11
     injective
    1.09
    POSITIVE LOGITS
    ৭
    1.45
    ين
    1.34
    í
    1.27
    ó
    1.23
    ס
    1.23
    ؤں
    1.16
    סת
    1.16
    да
    1.16
    ata
    1.15
    ים
    1.15
    Activations Density 0.156%

    No Known Activations