© 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. 31-GEMMASCOPE-2-RES-65K
    7. 12758
    Prev
    Next
    INDEX
    Explanations

    final arbiter of the Constitution

    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_31_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
    र्मा
    0.45
    ᶤ
    0.43
     rmse
    0.42
    iciable
    0.41
     வெளிய
    0.41
    iqué
    0.40
    iense
    0.39
    lden
    0.39
    谑
    0.39
    ativo
    0.39
    POSITIVE LOGITS
     Final
    0.46
     finale
    0.45
     objections
    0.44
     النهائية
    0.43
     tandem
    0.41
     final
    0.41
     Finale
    0.39
    Finale
    0.39
    Final
    0.39
     gw
    0.38
    Activations Density 0.001%

    No Known Activations