© 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. 84084
    Prev
    Next
    INDEX
    Explanations

    foreign conjunctions and phrases

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

    abstractive summarization

    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
    Pray
    0.51
     nulle
    0.50
    ור
    0.50
    ިން
    0.46
    victory
    0.46
    INAL
    0.44
    ಲಿಲ್ಲ
    0.44
    ර
    0.44
     pertanian
    0.43
     kurang
    0.42
    POSITIVE LOGITS
    和服务
    0.68
     και
    0.61
     এবং
    0.59
     và
    0.59
     आणि
    0.58
    และ
    0.58
     и
    0.57
     և
    0.52
    και
    0.51
    และความ
    0.51
    Activations Density 0.002%

    No Known Activations