© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 16326
    Prev
    Next
    INDEX
    Explanations

    referencing important notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_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
    !(
    0.41
    ச்சர்
    0.41
    )){
    0.39
    !)
    0.38
     conservatively
    0.38
    !:
    0.38
    !!
    0.38
    !!!!!!!
    0.38
     каче
    0.37
     darn
    0.36
    POSITIVE LOGITS
     NOTE
    0.62
     Note
    0.57
    Note
    0.55
     Notas
    0.54
     Notes
    0.52
    bottom
    0.52
    Nota
    0.52
    Примеча
    0.52
     NOTES
    0.51
     note
    0.51
    Activations Density 0.015%

    No Known Activations