© 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. 196681
    Prev
    Next
    INDEX
    Explanations

    gerunds followed by prepositions

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

    open-source models vs closed-source

    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
     ຊ
    0.57
     గౌ
    0.54
     남자
    0.49
     futuros
    0.48
     कदम
    0.48
     협
    0.48
     ກ
    0.48
     ダイ
    0.47
     कॉल
    0.47
     correcto
    0.47
    POSITIVE LOGITS
    F
    0.59
    There
    0.59
    Cor
    0.59
    Get
    0.57
    Marcel
    0.57
    En
    0.56
    O
    0.54
    ام
    0.53
    Tree
    0.53
    Al
    0.52
    Activations Density 0.001%

    No Known Activations