© 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. 12767
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases and verb phrases

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

    not just

    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
    医学
    0.40
     있고
    0.37
    FileInfo
    0.37
     wordArray
    0.36
    ཚ
    0.36
     तैया
    0.36
     छह
    0.36
    曾
    0.35
     डिफरेंट
    0.35
    经销
    0.35
    POSITIVE LOGITS
     übrigens
    0.46
     tuttavia
    0.44
     Zuf
    0.43
     azonban
    0.42
     nomencl
    0.41
     ancak
    0.41
     Bedarf
    0.39
     však
    0.38
     however
    0.38
     nostalg
    0.38
    Activations Density 0.196%

    No Known Activations