© 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. 16-GEMMASCOPE-2-RES-262K
    7. 40148
    Prev
    Next
    INDEX
    Explanations

    superlatives, extremes, or processes

    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_16_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
    මැ
    0.51
    ছিল
    0.49
    (−
    0.49
    setText
    0.47
    ěz
    0.47
    (*´
    0.47
    MoodAnalyser
    0.47
    үүн
    0.47
    ję
    0.47
    ág
    0.47
    POSITIVE LOGITS
     v
    0.55
     fair
    0.51
    A
    0.50
     Einen
    0.50
    sport
    0.50
    FOR
    0.49
     FOR
    0.49
     chr
    0.48
     SINGLE
    0.47
     EMPLOY
    0.46
    Activations Density 0.000%

    No Known Activations