© 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. 49176
    Prev
    Next
    INDEX
    Explanations

    insecticidal soap, ionized gases

    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
    s
    0.46
    ampton
    0.42
    o
    0.42
    eo
    0.41
    inoa
    0.41
     RAC
    0.39
    )/
    0.38
     SEO
    0.38
     ROI
    0.38
     Thursday
    0.38
    POSITIVE LOGITS
    ל
    0.48
     ayak
    0.46
    밋
    0.46
    ير
    0.45
    лови
    0.44
    महल
    0.44
     ব্রাজিল
    0.43
    וי
    0.43
     vond
    0.43
    лова
    0.42
    Activations Density 0.015%

    No Known Activations