© 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. 260
    Prev
    Next
    INDEX
    Explanations

    identifying and focusing on proper names of people, especially public/political figures.

    oai_token-act-pair · gpt-5-nanoTriggered by @nvasa7707
    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
    ॕ
    1.02
    මට
    0.91
    ेलकम
    0.81
    ंनो
    0.80
    ेंगू
    0.80
    ෙන්ම
    0.79
    ㅈ
    0.79
    ..");
    0.78
    စျေး
    0.77
    ্ের
    0.76
    POSITIVE LOGITS
     (
    5.25
    （
    4.10
     （
    3.72
    (
    3.61
     ([
    3.61
     ((
    3.51
     ("
    3.37
     (-
    3.28
     ('
    3.25
     ($
    3.21
    Activations Density 10.623%

    No Known Activations