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-16K
    4. 3157
    Prev
    Next
    INDEX
    Explanations

    expectations and predictions

    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
    THING
    1.54
     chiller
    1.52
     whitespace
    1.51
    在于
    1.49
     wrists
    1.44
     ngữ
    1.41
    ଼
    1.40
     purported
    1.37
    ┑
    1.36
    ness
    1.35
    POSITIVE LOGITS
    ك
    1.87
     podendo
    1.75
     viviendo
    1.69
    conoc
    1.65
    ate
    1.63
    Quando
    1.63
     tahmin
    1.60
    न
    1.60
    Nella
    1.59
    ajout
    1.56
    Activations Density 0.432%

    No Known Activations