© 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-16K
    7. 1861
    Prev
    Next
    INDEX
    Explanations

    ways of presenting

    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_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
    迤
    0.80
    Bibliographie
    0.78
     contradicting
    0.77
     sidan
    0.73
     related
    0.72
     balancing
    0.72
     Nearby
    0.72
     파인더
    0.71
     outlined
    0.71
    Interpretation
    0.71
    POSITIVE LOGITS
    जे
    0.55
     ways
    0.52
    फाली
    0.51
     tears
    0.49
    供
    0.49
     don
    0.49
     host
    0.48
     contrato
    0.47
     F
    0.47
    \%
    0.47
    Activations Density 0.339%

    No Known Activations