© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15860
    Prev
    Next
    INDEX
    Explanations

    exclamations and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite

    positive affirmations or requests

    np_acts-logits-general · gemini-2.5-flash-lite

    sentence endings

    np_max-act-logits · claude-4-5-sonnetTriggered by @sripadkarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     http
    0.59
     hehe
    0.50
     Bill
    0.49
    http
    0.48
     MUCH
    0.48
     i
    0.47
     today
    0.47
     it
    0.47
     Sure
    0.46
     you
    0.46
    POSITIVE LOGITS
     sogenannte
    0.46
     sogenannten
    0.44
     physicochemical
    0.39
    макраты
    0.38
    คาเดมี
    0.38
    Chúng
    0.37
    ⚌
    0.37
     civilisation
    0.36
    我們要
    0.36
     congested
    0.35
    Activations Density 0.066%

    No Known Activations