© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 1260
    Prev
    Next
    INDEX
    Explanations

    Linux, human, XGBoost

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
     지정
    0.65
    ����
    0.64
    ப்பட்டுள்ள
    0.64
    နာ
    0.60
     लागणार
    0.60
     besonder
    0.60
     adlı
    0.60
    ��������
    0.60
     নামের
    0.59
    �
    0.59
    POSITIVE LOGITS
     counterparts
    0.91
     でも
    0.81
    เคย
    0.81
     sekal
    0.79
     kebanyakan
    0.79
    詬
    0.78
    ówno
    0.75
     दिखता
    0.75
     například
    0.74
    那样
    0.73
    Activations Density 0.870%

    No Known Activations