© 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. 104146
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by specific grammatical phrases

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

    looking around or walking

    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
     Jahrhund
    0.48
     Đối
    0.48
    自己
    0.46
    𝘾
    0.46
    ürdig
    0.45
    笑
    0.44
    单
    0.44
     Überg
    0.43
    项目中
    0.43
    心中的
    0.43
    POSITIVE LOGITS
    ه
    0.51
    a
    0.50
     et
    0.48
    ONTAL
    0.48
    то
    0.47
    ;
    0.47
     तो
    0.46
     ማለት
    0.46
     ABI
    0.46
     LAG
    0.46
    Activations Density 0.001%

    No Known Activations