© 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-262K
    7. 7874
    Prev
    Next
    INDEX
    Explanations

    mayo

    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
    ā
    1.52
    ó
    1.51
     quente
    1.47
    ק
    1.46
    är
    1.44
    ДК
    1.41
    𝑇
    1.39
    iego
    1.38
    tex
    1.36
    是因为
    1.35
    POSITIVE LOGITS
    ро
    1.63
    ت
    1.52
    м
    1.41
    жи
    1.41
    きた
    1.28
     decency
    1.27
    じ
    1.26
    a
    1.23
    া
    1.12
    랄
    1.11
    Activations Density 0.002%

    No Known Activations