© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 28066
    Prev
    Next
    INDEX
    Explanations

    sarcastic or witty responses

    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
    ₂(
    0.39
    微生物
    0.39
    AssetDiscovery
    0.38
    Misc
    0.38
    บริเวณ
    0.37
     voies
    0.37
    ালী
    0.37
    Lng
    0.36
    ~(
    0.36
    作业
    0.35
    POSITIVE LOGITS
     Wasn
    0.46
     takže
    0.46
    icija
    0.45
    so
    0.44
     Didn
    0.43
     complicado
    0.43
    át
    0.41
     understatement
    0.41
     Isn
    0.41
     hahaha
    0.40
    Activations Density 0.022%

    No Known Activations