© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 8842
    Prev
    Next
    INDEX
    Explanations

    PyTorch, settings, matrix, training

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_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
     forceful
    0.66
     successive
    0.63
     steeply
    0.61
     semantic
    0.59
     centrally
    0.59
     centrality
    0.58
    酽
    0.57
     brooding
    0.56
     spurious
    0.55
     marginally
    0.55
    POSITIVE LOGITS
    зка
    0.58
    ك
    0.57
    以上
    0.56
    薯
    0.54
    മല്ല
    0.54
     daba
    0.52
    тным
    0.52
     подобные
    0.52
    ಕೊ
    0.51
    кими
    0.51
    Activations Density 4.586%

    No Known Activations