© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 49904
    Prev
    Next
    INDEX
    Explanations

    Title, alternative, or similar

    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
     उत्पा
    0.42
    ॠ
    0.42
    ovní
    0.40
    Political
    0.39
     POLITICAL
    0.38
    いますが
    0.37
     রাজনৈতিক
    0.37
     प्रदू
    0.37
    eliti
    0.37
    teaching
    0.36
    POSITIVE LOGITS
     chiffon
    0.40
     fellow
    0.39
    夎
    0.38
    棻
    0.38
     بیٹے
    0.37
     ස
    0.36
     Associated
    0.35
     ဆ
    0.35
     eponym
    0.35
     đế
    0.35
    Activations Density 0.004%

    No Known Activations