© 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. 13-GEMMASCOPE-2-RES-65K
    7. 1692
    Prev
    Next
    INDEX
    Explanations

    contrastive conjunctions

    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_13_width_65k_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
    ≔
    0.95
    들의
    0.85
     bloodshed
    0.83
     prélim
    0.83
     सपनों
    0.82
    ous
    0.81
     kematian
    0.81
     crescente
    0.79
     mund
    0.78
    ﹃
    0.78
    POSITIVE LOGITS
     However
    1.17
     however
    1.17
     although
    1.07
     but
    1.05
    However
    1.02
     однако
    0.99
    但是
    0.97
    但
    0.94
     depending
    0.91
     تاہم
    0.90
    Activations Density 0.630%

    No Known Activations