© 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-262K
    7. 5334
    Prev
    Next
    INDEX
    Explanations

    SQLAlchemy column definition

    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_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
     careless
    0.38
     (
    0.36
     możliwość
    0.36
     misguided
    0.35
    सामाजिक
    0.35
     Erkennt
    0.35
     sickening
    0.34
    ↵↵
    0.34
     reckless
    0.34
     مدیر
    0.34
    POSITIVE LOGITS
    loan
    0.37
    toHaveBeen
    0.33
    ion
    0.33
     لون
    0.33
    expandedTitle
    0.32
    épaisseur
    0.32
    লাইয়া
    0.31
     lezen
    0.31
    thisComponent
    0.31
     огне
    0.31
    Activations Density 0.000%

    No Known Activations