© 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. 31630
    Prev
    Next
    INDEX
    Explanations

    expose wrongdoing, unfairness, plots

    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
    씩
    1.57
    ől
    1.52
     chắn
    1.51
    ﺶ
    1.49
     obtenido
    1.46
     Fär
    1.45
     compuesta
    1.45
     angene
    1.43
    toadd
    1.43
     equação
    1.42
    POSITIVE LOGITS
    го
    1.57
    с
    1.43
    з
    1.41
    ep
    1.40
    aa
    1.38
    ن
    1.36
    ру
    1.34
    ть
    1.27
    a
    1.24
    라도
    1.23
    Activations Density 0.003%

    No Known Activations