© 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. 14824
    Prev
    Next
    INDEX
    Explanations

    keynotes and presentations

    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
     لعبة
    0.91
    낚
    0.89
     kidnapping
    0.84
     cooperate
    0.83
     aventuras
    0.81
     코드
    0.80
     işlemi
    0.80
     거래
    0.80
    ಃ
    0.77
     thỏa
    0.77
    POSITIVE LOGITS
     Presentations
    1.90
     presentations
    1.88
    演讲
    1.80
     Speakers
    1.79
     presentation
    1.73
     speaker
    1.73
    presentations
    1.71
     speakers
    1.68
     выступления
    1.68
    Speakers
    1.67
    Activations Density 0.109%

    No Known Activations