© 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. 391
    Prev
    Next
    INDEX
    Explanations

    intent recognition

    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
    ﺕ
    1.59
    다는
    1.58
     iż
    1.56
    "{
    1.52
    oration
    1.44
    层面
    1.41
    有些
    1.40
    ૂર્ણ
    1.40
    ুজ
    1.38
    가
    1.38
    POSITIVE LOGITS
    COME
    1.40
     Misalnya
    1.34
     রওনা
    1.34
     uhr
    1.30
    ف
    1.27
    ት
    1.27
     crucially
    1.25
    ContainsKey
    1.23
    কালীন
    1.20
     ablaze
    1.19
    Activations Density 0.027%

    No Known Activations