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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 68871
    Prev
    Next
    INDEX
    Explanations

    punctuation and the start of phrases

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

    tweets starting with common phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     tweeted
    0.58
     tweeting
    0.55
    球队
    0.54
     retweet
    0.51
    讓我
    0.46
     আওয়ামী
    0.45
    但我
    0.44
    徹
    0.44
     tweets
    0.42
     ट्वीट
    0.42
    POSITIVE LOGITS
    kens
    0.46
    bust
    0.46
    ;;
    0.46
    érico
    0.43
     প্রস্থ
    0.43
    ರುತ್ತವೆ
    0.43
    Наи
    0.42
    BLEND
    0.42
    BEAN
    0.42
    CLAS
    0.41
    Activations Density 0.001%

    No Known Activations