© 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. 16-GEMMASCOPE-2-RES-262K
    7. 31587
    Prev
    Next
    INDEX
    Explanations

    like burnt toast

    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_16_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
     nhớ
    0.52
     Using
    0.51
     Ashe
    0.49
     የተለያዩ
    0.49
     Weise
    0.47
     дина
    0.47
     株
    0.47
     recordó
    0.47
     Ensuring
    0.47
     Vorteile
    0.47
    POSITIVE LOGITS
    h
    0.51
     massages
    0.50
     prizes
    0.49
     synergies
    0.48
     reductions
    0.47
    ث
    0.46
     coupes
    0.46
    XI
    0.45
     équipe
    0.44
    خ
    0.44
    Activations Density 0.000%

    No Known Activations