© 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. 201977
    Prev
    Next
    INDEX
    Explanations

    dentistry is

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

    series funding rounds

    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
     bushing
    0.50
     maksimum
    0.49
     Ombudsman
    0.48
     ganglia
    0.46
     auditor
    0.46
     ڈیز
    0.44
    깐
    0.44
     suda
    0.43
     escalating
    0.41
     autochtones
    0.41
    POSITIVE LOGITS
     Вен
    0.53
    ПР
    0.50
     о
    0.50
     С
    0.48
     зна
    0.48
     развитие
    0.48
     переда
    0.47
     а
    0.47
     П
    0.47
     Затем
    0.47
    Activations Density 0.000%

    No Known Activations