Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 8344
    Prev
    Next
    INDEX
    Explanations

    chat dialogue

    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
     behest
    1.52
     punctures
    1.49
     sebaik
    1.48
     nhờ
    1.47
     decedent
    1.44
     multifaceted
    1.44
    贼
    1.44
    ння
    1.43
     encroach
    1.43
     riches
    1.42
    POSITIVE LOGITS
    on
    2.02
    ين
    1.88
    ลล์
    1.88
    Chat
    1.79
     Chat
    1.78
    ul
    1.69
    light
    1.67
    s
    1.64
    w
    1.63
    니다
    1.62
    Activations Density 0.067%

    No Known Activations