© 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. 61
    Prev
    Next
    INDEX
    Explanations

    objects and their descriptions

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

    environment, future, work, applications

    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
     (!)
    0.61
     beragam
    0.55
     Policy
    0.52
     Names
    0.48
     棉
    0.48
     —
    0.47
     文件
    0.47
    铁路
    0.47
     नगर
    0.47
     Admissions
    0.47
    POSITIVE LOGITS
    because
    0.77
     क्योंकि
    0.69
    เพราะ
    0.66
     because
    0.65
    Therefore
    0.61
    porque
    0.61
     ดังนั้น
    0.61
    क्योंकि
    0.60
     lessening
    0.60
    Hence
    0.59
    Activations Density 0.300%

    No Known Activations